Predicting Emerging Adulthood Outcomes from School Grades
###variable overview###
data available GCSE at 16 pcexdata1 TEDS21 phase 1 u1cdata1 TEDS21 phase 2 u2cdata1 age age web test 16 pcwebage1 age GCSE pcexgcseage1 age TEDS21 phase 1 u1cage1 age TEDS21 phase 2 u2cage1 sex sex1 SES SES index 1 (1st contact) ases SES index 2 (age 7) gses SES index 3 (income age 9) ipincome SES age 16 pses SES age 23 (TEDS 21) u1pses school performance (GCSE, age 16) pcexgcsecoregrdm1 (4-11, higher=better)
#outcomes (age 21) edu. attainment composite, standardised u1cedat1
still studying u1chqualp1 (1-11, higher=better) university performance
u1cdegr11 (2-5, higher=better) employment status u1cstatus1 (needs to be
recoded) recoded version 1 status1 (0-4, nominal) recoded binary
status_bin (0 = not in emp.:gap,parent,unemp.; 1 =
emp.:study,apprentice.,work) occupational prestige (SOC) u1csoc1 (1-9,
lower=better!) recoded version soc1 (0-8, higher=better) income monthly
emp. income u1cjobinc1 (1-9, higher=better) monthly not from work
u1cothinc1 benefit status (receive any) u1cbenf11 (0=no, 1=yes)
financial attitudes + behaviour u1cmonam1 (1-5, higher=better) financial
contentment w/ life (CLAS) u1cfinam1 (1-5, higher=better) wellbeing
(MFQ) u1cmfqt1 (0-16, lower=better! will be recoded) recoded version
wellb1 (0-16, higher=better) anxiety u2cganxt1 (0-40, lower=better/less
anxiety) behaviour problems (SDQ) u1csdqbeht1 (0-40, lower=better/less
problem behav.) alcohol use u2calcoaudit1 (0-40, lower=better/less
alcohol)
install/load packages
#Step 1: #Data preparation: Subset data, recode variables, get Z-scores, save datasets for analyses
#load data
dat <- read.spss("/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/557 Sophie von Stumm GCSE and emerging adulthood Apr2023.sav",use.value.label = FALSE, to.data.frame=TRUE)
dim(dat) #19984 339
## [1] 19984 339
#Save as csv file
write.csv(dat, '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth.csv', row.names = F, na = 'NA')
#And re-read
data <- read.csv("/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth.csv", header = T, strip.white = T,na.strings = c('NA', '', ' '
))
dim(data) #19984 339
## [1] 19984 339
#str(data)
df<- data[, c('randomfamid', 'randomtwinid', 'twin', 'random', 'cohort', 'sex1', 'sex2', 'zygos',
'sexzyg', 'x3zygos', 'acontact', 'medexcl1', 'exclude1', 'ases', 'gses', 'pses', 'u1pses', 'ipincome',
'pcexdata1', 'u1cdata1', 'u2cdata1','pcwebage1', 'pcexgcseage1', 'u1cage1', 'u2cage1',
'pcexgcsecoregrdm1', 'u1cedat1', 'u1chqualp1', 'u1cdegr11',
'u1cstatus1', 'u1csoc1', 'u1cjobinc1', 'u1cbenf11',
'u1cmona11', 'u1cmona1r1', 'u1cmona21', 'u1cmona2r1', 'u1cmona31', 'u1cmona41',
'u1cmona51', 'u1cmona61', 'u1cmona6r1', 'u1cmonam1',
'u1cfinam1', 'u1cfina11', 'u1cfina21', 'u1cfina31', 'u1cfina41', 'u1cfina51', 'u1cfina5r1',
'u1cmfqt1', 'u1cmfq11', 'u1cmfq21', 'u1cmfq31', 'u1cmfq41', 'u1cmfq51', 'u1cmfq61', 'u1cmfq71', 'u1cmfq81',
'u2cganxt1', 'u2cganx011', 'u2cganx021', 'u2cganx031', 'u2cganx041', 'u2cganx051',
'u2cganx061', 'u2cganx071', 'u2cganx081', 'u2cganx091', 'u2cganx101',
'u1csdqbeht1', 'u1csdqemot1', 'u1csdqcont1', 'u1csdqhypt1', 'u1csdqpert1',
'u2calcoaudit1', 'u2calco041', 'u2calco051', 'u2calco061', 'u2calco071', 'u2calco081',
'u2calco091', 'u2calco101', 'u2calco111', 'u2calco121', 'u2calco131'),]
dim(df) #19984 86
## [1] 19984 86
#str(df)
write.csv(df, '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_reduced.csv', row.names = F, na = 'NA')
rm(list=ls())
ls()
## character(0)
#initial sample size
df <- read.csv("/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_reduced.csv", header = T, strip.white = T,na.strings = c('NA', '', ' '
))
dim(df) #19984 86
## [1] 19984 86
#sample size after medical exclusions
df1 = df[df$exclude1==0, ]
dim(df1) #18946 86
## [1] 18946 86
#exclude all cases with missing value on GCSE --> still keep both twins for data prep and later for multi-group regressions
freq(df1$pcexgcsecoregrdm1)
## Frequencies
## df1$pcexgcsecoregrdm1
## Type: Numeric
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ----------- ------- ---------- -------------- ---------- --------------
## 4 10 0.0770 0.0770 0.0528 0.0528
## 4.3 3 0.0231 0.1001 0.0158 0.0686
## 4.5 11 0.0847 0.1849 0.0581 0.1267
## 4.7 11 0.0847 0.2696 0.0581 0.1847
## 4.8 1 0.0077 0.2773 0.0053 0.1900
## 5 48 0.3698 0.6471 0.2534 0.4434
## 5.2 3 0.0231 0.6702 0.0158 0.4592
## 5.3 17 0.1310 0.8012 0.0897 0.5489
## 5.4 10 0.0770 0.8782 0.0528 0.6017
## 5.5 26 0.2003 1.0785 0.1372 0.7389
## 5.6 5 0.0385 1.1170 0.0264 0.7653
## 5.7 32 0.2465 1.3635 0.1689 0.9342
## 5.8 16 0.1233 1.4868 0.0845 1.0187
## 6 112 0.8628 2.3496 0.5912 1.6098
## 6.2 15 0.1156 2.4651 0.0792 1.6890
## 6.3 62 0.4776 2.9428 0.3272 2.0163
## 6.4 14 0.1078 3.0506 0.0739 2.0902
## 6.5 86 0.6625 3.7131 0.4539 2.5441
## 6.6 24 0.1849 3.8980 0.1267 2.6707
## 6.7 64 0.4930 4.3910 0.3378 3.0086
## 6.8 85 0.6548 5.0458 0.4486 3.4572
## 7 288 2.2186 7.2645 1.5201 4.9773
## 7.1 1 0.0077 7.2722 0.0053 4.9826
## 7.2 91 0.7010 7.9732 0.4803 5.4629
## 7.3 230 1.7718 9.7450 1.2140 6.6769
## 7.4 120 0.9244 10.6694 0.6334 7.3103
## 7.5 254 1.9567 12.6261 1.3407 8.6509
## 7.6 154 1.1863 13.8125 0.8128 9.4637
## 7.7 203 1.5638 15.3763 1.0715 10.5352
## 7.8 468 3.6053 18.9816 2.4702 13.0054
## 7.9 12 0.0924 19.0740 0.0633 13.0687
## 8 919 7.0796 26.1536 4.8506 17.9193
## 8.1 15 0.1156 26.2692 0.0792 17.9985
## 8.2 466 3.5899 29.8590 2.4596 20.4581
## 8.3 438 3.3742 33.2332 2.3118 22.7700
## 8.4 368 2.8349 36.0681 1.9424 24.7123
## 8.5 351 2.7040 38.7721 1.8526 26.5650
## 8.6 408 3.1431 41.9151 2.1535 28.7185
## 8.7 301 2.3188 44.2339 1.5887 30.3072
## 8.8 664 5.1152 49.3490 3.5047 33.8119
## 8.9 40 0.3081 49.6572 0.2111 34.0230
## 9 708 5.4541 55.1113 3.7369 37.7599
## 9.1 39 0.3004 55.4118 0.2058 37.9658
## 9.2 568 4.3756 59.7874 2.9980 40.9638
## 9.3 362 2.7887 62.5761 1.9107 42.8745
## 9.4 335 2.5807 65.1568 1.7682 44.6427
## 9.5 331 2.5499 67.7066 1.7471 46.3897
## 9.6 286 2.2032 69.9099 1.5096 47.8993
## 9.7 337 2.5961 72.5060 1.7787 49.6780
## 9.8 495 3.8133 76.3192 2.6127 52.2907
## 9.9 56 0.4314 76.7506 0.2956 52.5863
## 10 535 4.1214 80.8720 2.8238 55.4101
## 10.1 68 0.5238 81.3959 0.3589 55.7690
## 10.2 407 3.1354 84.5312 2.1482 57.9172
## 10.3 316 2.4343 86.9656 1.6679 59.5851
## 10.4 201 1.5484 88.5140 1.0609 60.6460
## 10.5 254 1.9567 90.4707 1.3407 61.9867
## 10.6 159 1.2249 91.6956 0.8392 62.8259
## 10.7 297 2.2880 93.9835 1.5676 64.3935
## 10.8 342 2.6346 96.6181 1.8051 66.1987
## 10.9 62 0.4776 97.0958 0.3272 66.5259
## 11 377 2.9042 100.0000 1.9899 68.5158
## <NA> 5965 31.4842 100.0000
## Total 18946 100.0000 100.0000 100.0000 100.0000
df2 = df1[is.na(df1$pcexgcsecoregrdm1) == FALSE, ]
#check that NA=0
freq(df2$pcexgcsecoregrdm1)
## Frequencies
## df2$pcexgcsecoregrdm1
## Type: Numeric
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ----------- ------- ---------- -------------- ---------- --------------
## 4 10 0.0770 0.0770 0.0770 0.0770
## 4.3 3 0.0231 0.1001 0.0231 0.1001
## 4.5 11 0.0847 0.1849 0.0847 0.1849
## 4.7 11 0.0847 0.2696 0.0847 0.2696
## 4.8 1 0.0077 0.2773 0.0077 0.2773
## 5 48 0.3698 0.6471 0.3698 0.6471
## 5.2 3 0.0231 0.6702 0.0231 0.6702
## 5.3 17 0.1310 0.8012 0.1310 0.8012
## 5.4 10 0.0770 0.8782 0.0770 0.8782
## 5.5 26 0.2003 1.0785 0.2003 1.0785
## 5.6 5 0.0385 1.1170 0.0385 1.1170
## 5.7 32 0.2465 1.3635 0.2465 1.3635
## 5.8 16 0.1233 1.4868 0.1233 1.4868
## 6 112 0.8628 2.3496 0.8628 2.3496
## 6.2 15 0.1156 2.4651 0.1156 2.4651
## 6.3 62 0.4776 2.9428 0.4776 2.9428
## 6.4 14 0.1078 3.0506 0.1078 3.0506
## 6.5 86 0.6625 3.7131 0.6625 3.7131
## 6.6 24 0.1849 3.8980 0.1849 3.8980
## 6.7 64 0.4930 4.3910 0.4930 4.3910
## 6.8 85 0.6548 5.0458 0.6548 5.0458
## 7 288 2.2186 7.2645 2.2186 7.2645
## 7.1 1 0.0077 7.2722 0.0077 7.2722
## 7.2 91 0.7010 7.9732 0.7010 7.9732
## 7.3 230 1.7718 9.7450 1.7718 9.7450
## 7.4 120 0.9244 10.6694 0.9244 10.6694
## 7.5 254 1.9567 12.6261 1.9567 12.6261
## 7.6 154 1.1863 13.8125 1.1863 13.8125
## 7.7 203 1.5638 15.3763 1.5638 15.3763
## 7.8 468 3.6053 18.9816 3.6053 18.9816
## 7.9 12 0.0924 19.0740 0.0924 19.0740
## 8 919 7.0796 26.1536 7.0796 26.1536
## 8.1 15 0.1156 26.2692 0.1156 26.2692
## 8.2 466 3.5899 29.8590 3.5899 29.8590
## 8.3 438 3.3742 33.2332 3.3742 33.2332
## 8.4 368 2.8349 36.0681 2.8349 36.0681
## 8.5 351 2.7040 38.7721 2.7040 38.7721
## 8.6 408 3.1431 41.9151 3.1431 41.9151
## 8.7 301 2.3188 44.2339 2.3188 44.2339
## 8.8 664 5.1152 49.3490 5.1152 49.3490
## 8.9 40 0.3081 49.6572 0.3081 49.6572
## 9 708 5.4541 55.1113 5.4541 55.1113
## 9.1 39 0.3004 55.4118 0.3004 55.4118
## 9.2 568 4.3756 59.7874 4.3756 59.7874
## 9.3 362 2.7887 62.5761 2.7887 62.5761
## 9.4 335 2.5807 65.1568 2.5807 65.1568
## 9.5 331 2.5499 67.7066 2.5499 67.7066
## 9.6 286 2.2032 69.9099 2.2032 69.9099
## 9.7 337 2.5961 72.5060 2.5961 72.5060
## 9.8 495 3.8133 76.3192 3.8133 76.3192
## 9.9 56 0.4314 76.7506 0.4314 76.7506
## 10 535 4.1214 80.8720 4.1214 80.8720
## 10.1 68 0.5238 81.3959 0.5238 81.3959
## 10.2 407 3.1354 84.5312 3.1354 84.5312
## 10.3 316 2.4343 86.9656 2.4343 86.9656
## 10.4 201 1.5484 88.5140 1.5484 88.5140
## 10.5 254 1.9567 90.4707 1.9567 90.4707
## 10.6 159 1.2249 91.6956 1.2249 91.6956
## 10.7 297 2.2880 93.9835 2.2880 93.9835
## 10.8 342 2.6346 96.6181 2.6346 96.6181
## 10.9 62 0.4776 97.0958 0.4776 97.0958
## 11 377 2.9042 100.0000 2.9042 100.0000
## <NA> 0 0.0000 100.0000
## Total 12981 100.0000 100.0000 100.0000 100.0000
dim(df2) #12981 86
## [1] 12981 86
#recode employment status: 2 versions
#old
#1=studying; 2=working; 3=apprenticeship; 4=gap year/travelling; 5=unemployed; 6=full-time parent
#new
#1) nominal (as described in prereg)
#0=unemployed; 1=working; 2=studying or apprenticeship; 3=full-time parents; 4=gap year/travelling
df2 <- df2 %>%
mutate(status1 = ifelse(u1cstatus1 == 5, 0,
ifelse(u1cstatus1 == 2, 1,
ifelse(u1cstatus1 %in% c(1,3), 2,
ifelse(u1cstatus1 == 6, 3,
ifelse(u1cstatus1 == 4, 4, NA))))))
#check frequencies after recoding
table(df2$u1cstatus1)
##
## 1 2 3 4 5 6
## 2567 3899 288 246 462 57
table(df2$status1)
##
## 0 1 2 3 4
## 462 3899 2855 57 246
#2) binary
#0 = not in full-time employment (unemployed,parent,gap year); 1 = in education/full-time work
df2 <- df2 %>%
mutate(status_bin = ifelse(u1cstatus1 %in% c(1,2,3), 1,
ifelse(u1cstatus1 %in% c(4,5,6), 0, NA)))
#check frequencies after recoding
table(df2$u1cstatus1)
##
## 1 2 3 4 5 6
## 2567 3899 288 246 462 57
table(df2$status_bin)
##
## 0 1
## 765 6754
#reverse wellbeing -> so higher = better
describe(df2$u1cmfqt1) #max = 16
## df2$u1cmfqt1
## n missing distinct Info Mean Gmd .05 .10
## 7544 5437 20 0.988 4.332 4.404 0 0
## .25 .50 .75 .90 .95
## 1 3 7 11 13
##
## lowest : 0.000000 1.000000 1.142857 2.000000 2.285714
## highest: 12.000000 13.000000 14.000000 15.000000 16.000000
##
## 0 (1290, 0.171), 1 (1046, 0.139), 1.14285714285714 (1, 0.000), 2 (899, 0.119),
## 2.28571428571429 (2, 0.000), 3 (762, 0.101), 4 (659, 0.087), 5 (530, 0.070), 6
## (415, 0.055), 7 (391, 0.052), 8 (294, 0.039), 9 (253, 0.034), 10 (216, 0.029),
## 10.2857142857143 (1, 0.000), 11 (210, 0.028), 12 (141, 0.019), 13 (130, 0.017),
## 14 (115, 0.015), 15 (95, 0.013), 16 (94, 0.012)
df2 <- df2 %>%
mutate(wellb1 = 16 - u1cmfqt1)
#reverse occupational prestige (SOC) -> higher = better
describe(df2$u1csoc1) #max = 9
## df2$u1csoc1
## n missing distinct Info Mean Gmd
## 3453 9528 9 0.969 4.333 2.55
##
## lowest : 1 2 3 4 5, highest: 5 6 7 8 9
##
## Value 1 2 3 4 5 6 7 8 9
## Frequency 173 699 859 360 163 339 580 54 226
## Proportion 0.050 0.202 0.249 0.104 0.047 0.098 0.168 0.016 0.065
df2 <- df2 %>%
mutate(soc1 = 9 - u1csoc1)
dim(df2) #12981 90
## [1] 12981 90
#standardise variables separately for twin 1 and 2 (random=0/1), then merge datasets again
df_scaled0 <- df2 %>% filter(random == 0) %>%
mutate(Zgcse = scale(pcexgcsecoregrdm1)) %>%
mutate(Zhqual = scale(u1chqualp1)) %>%
mutate(Zdegree = scale(u1cdegr11)) %>%
mutate(Zsoc = scale(soc1)) %>%
mutate(Zinc = scale(u1cjobinc1)) %>%
mutate(Zmon = scale(u1cmonam1)) %>%
mutate(Zfina = scale(u1cfinam1)) %>%
mutate(Zwellb = scale(wellb1)) %>%
mutate(Zanx = scale(u2cganxt1)) %>%
mutate(Zsdq = scale(u1csdqbeht1)) %>%
mutate(Zalc = scale(u2calcoaudit1)) %>%
mutate(Zases = scale(ases)) %>%
mutate(Zgses = scale(gses)) %>%
mutate(Zpses = scale(pses)) %>%
mutate(Zu1pses = scale(u1pses)) %>%
mutate(Zipincome = scale(ipincome))
df_scaled1 <- df2 %>% filter(random == 1) %>%
mutate(Zgcse = scale(pcexgcsecoregrdm1)) %>%
mutate(Zhqual = scale(u1chqualp1)) %>%
mutate(Zdegree = scale(u1cdegr11)) %>%
mutate(Zsoc = scale(soc1)) %>%
mutate(Zinc = scale(u1cjobinc1)) %>%
mutate(Zmon = scale(u1cmonam1)) %>%
mutate(Zfina = scale(u1cfinam1)) %>%
mutate(Zwellb = scale(wellb1)) %>%
mutate(Zanx = scale(u2cganxt1)) %>%
mutate(Zsdq = scale(u1csdqbeht1)) %>%
mutate(Zalc = scale(u2calcoaudit1)) %>%
mutate(Zases = scale(ases)) %>%
mutate(Zgses = scale(gses)) %>%
mutate(Zpses = scale(pses)) %>%
mutate(Zu1pses = scale(u1pses)) %>%
mutate(Zipincome = scale(ipincome))
df3 <- rbind(df_scaled0, df_scaled1)
#create SESscore from SES index 1, 2 & 3 (composite at 1st contact, age 7 and income at age 9)
df3$SESscore <- rowMeans(df3[c("Zipincome", "Zases", "Zgses")], na.rm = TRUE)
df3[sapply(df3, is.nan)] <- NA
dim(df3) #12981 107
## [1] 12981 107
Save two versions of prepared dataset for analyses
#1) prepared data, both twins
write.csv(df3, '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_bothtwins.csv', row.names = F, na = 'NA')
#select one random twin per pair
df4 = df3[df3$random==1, ]
dim(df4) #6488 107
## [1] 6488 107
#2) prepared data, one random twin
write.csv(df4, '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_random1.csv', row.names = F, na = 'NA')
#Step 2: #Preliminary analyses: Descriptives, correlations and Cronbach’s alpha
rm(list=ls())
ls()
## character(0)
#read in random1-dataset for preliminary analyses
df <- read.csv("/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_random1.csv", header = T, strip.white = T,na.strings = c('NA', '', ' '
))
desc = psych::describe(df[, c('pcwebage1', 'pcexgcseage1', 'u1cage1', 'u2cage1',
'pcexgcsecoregrdm1', 'u1cedat1', 'u1chqualp1', 'u1cdegr11', 'status1', 'status_bin', 'soc1', 'u1cjobinc1', 'u1cbenf11',
'u1cmonam1', 'u1cfinam1', 'wellb1', 'u2cganxt1', 'u1csdqbeht1', 'u2calcoaudit1')])
write.xlsx(desc, file = "/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/descriptives_grades_adulth.xlsx", col.names = TRUE, row.names = TRUE)
#frequencies for categorical variables
library(summarytools)
freq_hqual <- freq(df$u1chqualp1)
freq_status1 <- freq(df$status1)
freq_status_bin <- freq(df$status_bin)
freq_ocprestige <- freq(df$soc1)
freq_benf <- freq(df$u1cbenf11)
#correlations only for continuous variables
library(tidyverse)
library(ggcorrplot)
corrmatrix <- subset(df, select = c('pcexgcsecoregrdm1', 'u1cedat1', 'u1chqualp1', 'u1cdegr11', 'soc1', 'u1cjobinc1',
'u1cmonam1', 'u1cfinam1', 'wellb1', 'u2cganxt1', 'u1csdqbeht1', 'u2calcoaudit1'))
corrdata1matrix <- cor(corrmatrix, use = "pairwise.complete.obs", method = c ("pearson")) #produce correlation matrix
ggcorrplot(corrdata1matrix, ggtheme = ggplot2::theme_minimal, type = "lower", show.diag = TRUE,
lab = TRUE, lab_size = 3, tl.cex = 15, colors = c("#6D9EC1", "white", "red"))
ggsave("corrplot_grades_adulth.png")
## Saving 7 x 5 in image
#cor_pmat(corrdata1matrix) # p-values
#does the same but nicer tables imo
library(corrtable)
dffullcorr <- df %>% select(pcexgcsecoregrdm1, u1cedat1, u1chqualp1, u1cdegr11, soc1, u1cjobinc1,
u1cmonam1, u1cfinam1, wellb1, u2cganxt1, u1csdqbeht1, u2calcoaudit1)
correlation_matrix(
dffullcorr,
use = "lower")
## pcexgcsecoregrdm1 u1cedat1 u1chqualp1 u1cdegr11
## pcexgcsecoregrdm1 " 1.000 " "" "" ""
## u1cedat1 " 0.535***" " 1.000 " "" ""
## u1chqualp1 " 0.529***" " 0.967***" " 1.000 " ""
## u1cdegr11 " 0.284***" " 0.899***" " 0.147***" " 1.000 "
## soc1 " 0.290***" " 0.286***" " 0.279***" " 0.124***"
## u1cjobinc1 " 0.181***" " 0.111***" " 0.094***" " 0.103** "
## u1cmonam1 " 0.050** " " 0.036* " " 0.033* " " 0.076** "
## u1cfinam1 " 0.007 " "-0.046** " "-0.060***" " 0.095***"
## wellb1 " 0.110***" " 0.082***" " 0.086***" " 0.035 "
## u2cganxt1 "-0.015 " "-0.001 " "-0.010 " " 0.020 "
## u1csdqbeht1 "-0.216***" "-0.181***" "-0.184***" "-0.065** "
## u2calcoaudit1 " 0.033 " " 0.051** " " 0.045* " "-0.008 "
## soc1 u1cjobinc1 u1cmonam1 u1cfinam1 wellb1
## pcexgcsecoregrdm1 "" "" "" "" ""
## u1cedat1 "" "" "" "" ""
## u1chqualp1 "" "" "" "" ""
## u1cdegr11 "" "" "" "" ""
## soc1 " 1.000 " "" "" "" ""
## u1cjobinc1 " 0.420***" " 1.000 " "" "" ""
## u1cmonam1 " 0.132***" " 0.125***" " 1.000 " "" ""
## u1cfinam1 " 0.183***" " 0.321***" " 0.411***" " 1.000 " ""
## wellb1 " 0.180***" " 0.149***" " 0.175***" " 0.280***" " 1.000 "
## u2cganxt1 "-0.086** " "-0.126***" "-0.098***" "-0.245***" "-0.561***"
## u1csdqbeht1 "-0.194***" "-0.141***" "-0.206***" "-0.268***" "-0.759***"
## u2calcoaudit1 "-0.036 " " 0.036 " "-0.251***" "-0.138***" "-0.136***"
## u2cganxt1 u1csdqbeht1 u2calcoaudit1
## pcexgcsecoregrdm1 "" "" ""
## u1cedat1 "" "" ""
## u1chqualp1 "" "" ""
## u1cdegr11 "" "" ""
## soc1 "" "" ""
## u1cjobinc1 "" "" ""
## u1cmonam1 "" "" ""
## u1cfinam1 "" "" ""
## wellb1 "" "" ""
## u2cganxt1 " 1.000 " "" ""
## u1csdqbeht1 " 0.553***" " 1.000 " ""
## u2calcoaudit1 " 0.117***" " 0.095***" " 1.000 "
save_correlation_matrix(df = dffullcorr,
filename = '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/correlations_grades_adulth.csv',
digits = 3,
use = 'lower')
Cronbach’s alpha for all psychometric scales used to assess emerging adulthood outcomes (i.e., financial attitudes and behaviour, financial contentment with life, wellbeing, anxiety, behaviour problems)
library(psych)
#financial/money attitudes
monitems <- subset(df, select = c("u1cmona1r1", "u1cmona2r1", "u1cmona31", "u1cmona41", "u1cmona51", "u1cmona6r1"))
psych::alpha(monitems)
##
## Reliability analysis
## Call: psych::alpha(x = monitems)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.71 0.71 0.71 0.29 2.5 0.0054 3.6 0.6 0.3
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.7 0.71 0.72
## Duhachek 0.7 0.71 0.72
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## u1cmona1r1 0.67 0.67 0.67 0.29 2.1 0.0063 0.024 0.31
## u1cmona2r1 0.64 0.64 0.63 0.26 1.8 0.0070 0.020 0.27
## u1cmona31 0.70 0.70 0.68 0.32 2.3 0.0059 0.016 0.31
## u1cmona41 0.65 0.64 0.62 0.26 1.8 0.0067 0.015 0.27
## u1cmona51 0.67 0.67 0.65 0.29 2.0 0.0063 0.017 0.29
## u1cmona6r1 0.71 0.71 0.69 0.33 2.5 0.0056 0.010 0.31
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## u1cmona1r1 3661 0.66 0.64 0.53 0.45 3.5 0.99
## u1cmona2r1 3660 0.73 0.72 0.65 0.55 3.4 1.03
## u1cmona31 3655 0.53 0.58 0.45 0.37 4.3 0.71
## u1cmona41 3658 0.70 0.71 0.66 0.54 3.9 0.91
## u1cmona51 3658 0.67 0.65 0.56 0.46 3.3 1.06
## u1cmona6r1 3659 0.54 0.54 0.39 0.33 2.9 0.90
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## u1cmona1r1 0.02 0.17 0.22 0.45 0.14 0.44
## u1cmona2r1 0.03 0.19 0.22 0.43 0.13 0.44
## u1cmona31 0.00 0.02 0.08 0.50 0.40 0.44
## u1cmona41 0.01 0.09 0.16 0.51 0.23 0.44
## u1cmona51 0.03 0.23 0.26 0.34 0.13 0.44
## u1cmona6r1 0.03 0.31 0.39 0.23 0.04 0.44
#financial contentment with life
finaitems <- subset(df, select = c("u1cfina11", "u1cfina21", "u1cfina31", "u1cfina41", "u1cfina5r1"))
psych::alpha(finaitems)
##
## Reliability analysis
## Call: psych::alpha(x = finaitems)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.83 0.84 0.82 0.51 5.2 0.0033 3.7 0.81 0.49
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.83 0.83 0.84
## Duhachek 0.83 0.83 0.84
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## u1cfina11 0.79 0.80 0.75 0.49 3.9 0.0043 0.0070 0.49
## u1cfina21 0.77 0.78 0.74 0.47 3.5 0.0047 0.0083 0.46
## u1cfina31 0.84 0.84 0.80 0.56 5.2 0.0033 0.0075 0.57
## u1cfina41 0.78 0.78 0.75 0.47 3.6 0.0045 0.0111 0.46
## u1cfina5r1 0.82 0.82 0.79 0.54 4.7 0.0038 0.0136 0.54
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## u1cfina11 3662 0.80 0.80 0.75 0.67 3.7 1.12
## u1cfina21 3663 0.84 0.84 0.80 0.73 3.4 1.08
## u1cfina31 3662 0.71 0.69 0.56 0.51 3.5 1.18
## u1cfina41 3662 0.82 0.83 0.78 0.72 3.9 0.91
## u1cfina5r1 3661 0.72 0.73 0.62 0.57 3.9 0.95
##
## Non missing response frequency for each item
## 1 2 3 4 5 miss
## u1cfina11 0.06 0.12 0.13 0.47 0.22 0.44
## u1cfina21 0.06 0.16 0.24 0.41 0.13 0.44
## u1cfina31 0.05 0.18 0.17 0.37 0.23 0.44
## u1cfina41 0.03 0.07 0.11 0.59 0.20 0.44
## u1cfina5r1 0.01 0.09 0.16 0.45 0.29 0.44
#wellbeing
wellbitems <- subset(df, select = c("u1cmfq11", "u1cmfq21", "u1cmfq31", "u1cmfq41", "u1cmfq51", "u1cmfq61", "u1cmfq71", "u1cmfq81"))
psych::alpha(wellbitems)
##
## Reliability analysis
## Call: psych::alpha(x = wellbitems)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.87 0.87 0.87 0.46 6.9 0.0024 0.53 0.51 0.46
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.87 0.87 0.88
## Duhachek 0.87 0.87 0.88
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## u1cmfq11 0.84 0.85 0.83 0.44 5.5 0.0030 0.0057 0.43
## u1cmfq21 0.86 0.86 0.86 0.48 6.4 0.0026 0.0074 0.48
## u1cmfq31 0.87 0.87 0.86 0.49 6.6 0.0025 0.0051 0.48
## u1cmfq41 0.86 0.86 0.85 0.47 6.2 0.0027 0.0071 0.46
## u1cmfq51 0.86 0.86 0.85 0.46 6.0 0.0027 0.0085 0.44
## u1cmfq61 0.85 0.85 0.84 0.45 5.7 0.0028 0.0055 0.45
## u1cmfq71 0.85 0.85 0.84 0.46 5.9 0.0028 0.0063 0.45
## u1cmfq81 0.86 0.86 0.85 0.47 6.1 0.0027 0.0063 0.46
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## u1cmfq11 3753 0.81 0.81 0.79 0.74 0.63 0.74
## u1cmfq21 3753 0.69 0.68 0.61 0.57 0.77 0.76
## u1cmfq31 3753 0.64 0.64 0.56 0.52 0.51 0.67
## u1cmfq41 3754 0.69 0.70 0.64 0.60 0.29 0.59
## u1cmfq51 3753 0.73 0.74 0.69 0.64 0.50 0.66
## u1cmfq61 3753 0.78 0.78 0.75 0.70 0.35 0.64
## u1cmfq71 3754 0.76 0.76 0.71 0.67 0.55 0.72
## u1cmfq81 3753 0.73 0.72 0.67 0.61 0.66 0.76
##
## Non missing response frequency for each item
## 0 1 2 miss
## u1cmfq11 0.53 0.32 0.15 0.42
## u1cmfq21 0.43 0.37 0.20 0.42
## u1cmfq31 0.59 0.31 0.10 0.42
## u1cmfq41 0.78 0.15 0.07 0.42
## u1cmfq51 0.59 0.31 0.10 0.42
## u1cmfq61 0.74 0.17 0.09 0.42
## u1cmfq71 0.58 0.28 0.14 0.42
## u1cmfq81 0.52 0.31 0.18 0.42
#anxiety
anxitems <- subset(df, select = c("u2cganx011", "u2cganx021", "u2cganx031",
"u2cganx041", "u2cganx051", "u2cganx061", "u2cganx071", "u2cganx081",
"u2cganx091", "u2cganx101"))
psych::alpha(anxitems)
##
## Reliability analysis
## Call: psych::alpha(x = anxitems)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.91 0.91 0.91 0.51 11 0.0016 0.71 0.72 0.5
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.91 0.91 0.91
## Duhachek 0.91 0.91 0.91
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## u2cganx011 0.90 0.91 0.90 0.52 9.6 0.0017 0.0055 0.50
## u2cganx021 0.90 0.90 0.90 0.50 8.9 0.0019 0.0044 0.48
## u2cganx031 0.90 0.91 0.90 0.52 9.7 0.0017 0.0057 0.50
## u2cganx041 0.90 0.90 0.90 0.51 9.4 0.0018 0.0055 0.49
## u2cganx051 0.90 0.90 0.90 0.51 9.4 0.0018 0.0053 0.49
## u2cganx061 0.90 0.90 0.90 0.51 9.3 0.0018 0.0045 0.49
## u2cganx071 0.90 0.90 0.90 0.51 9.3 0.0018 0.0050 0.49
## u2cganx081 0.90 0.90 0.90 0.50 9.2 0.0018 0.0047 0.49
## u2cganx091 0.91 0.91 0.90 0.52 9.8 0.0017 0.0047 0.51
## u2cganx101 0.91 0.91 0.91 0.53 10.2 0.0017 0.0043 0.51
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## u2cganx011 3429 0.71 0.73 0.69 0.65 0.43 0.77
## u2cganx021 3429 0.83 0.83 0.81 0.78 1.35 1.07
## u2cganx031 3429 0.72 0.72 0.68 0.65 0.73 0.97
## u2cganx041 3428 0.74 0.75 0.72 0.68 0.50 0.84
## u2cganx051 3429 0.77 0.76 0.73 0.70 0.92 1.05
## u2cganx061 3429 0.77 0.77 0.75 0.71 0.62 0.95
## u2cganx071 3429 0.76 0.77 0.75 0.71 0.41 0.83
## u2cganx081 3429 0.80 0.79 0.76 0.73 0.83 1.08
## u2cganx091 3429 0.72 0.71 0.67 0.64 0.92 1.07
## u2cganx101 3429 0.65 0.66 0.60 0.57 0.36 0.94
##
## Non missing response frequency for each item
## 0 1 2 3 4 miss
## u2cganx011 0.69 0.23 0.04 0.03 0.01 0.47
## u2cganx021 0.20 0.46 0.17 0.12 0.05 0.47
## u2cganx031 0.52 0.33 0.08 0.05 0.02 0.47
## u2cganx041 0.66 0.24 0.06 0.03 0.01 0.47
## u2cganx051 0.44 0.34 0.12 0.08 0.03 0.47
## u2cganx061 0.61 0.26 0.07 0.05 0.02 0.47
## u2cganx071 0.74 0.17 0.04 0.03 0.01 0.47
## u2cganx081 0.50 0.30 0.09 0.07 0.03 0.47
## u2cganx091 0.44 0.35 0.10 0.08 0.03 0.47
## u2cganx101 0.83 0.08 0.02 0.03 0.04 0.47
#behaviour problems
SDQitems <- subset(df, select = c("u1csdqemot1", "u1csdqcont1", "u1csdqhypt1", "u1csdqpert1"))
psych::alpha(SDQitems)
## Number of categories should be increased in order to count frequencies.
##
## Reliability analysis
## Call: psych::alpha(x = SDQitems)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.66 0.67 0.62 0.33 2 0.0062 2.6 1.4 0.34
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.64 0.66 0.67
## Duhachek 0.65 0.66 0.67
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## u1csdqemot1 0.54 0.56 0.47 0.30 1.3 0.0092 0.0067 0.30
## u1csdqcont1 0.65 0.66 0.57 0.39 1.9 0.0070 0.0064 0.42
## u1csdqhypt1 0.53 0.55 0.47 0.29 1.2 0.0085 0.0118 0.25
## u1csdqpert1 0.60 0.63 0.54 0.36 1.7 0.0075 0.0108 0.38
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## u1csdqemot1 3755 0.82 0.75 0.63 0.53 3.5 2.7
## u1csdqcont1 3755 0.54 0.65 0.45 0.36 1.5 1.2
## u1csdqhypt1 3755 0.77 0.75 0.64 0.52 3.2 2.2
## u1csdqpert1 3755 0.66 0.68 0.51 0.43 2.1 1.7
Compare the average family SES of those who participated at age 16 and those who participated at age 23
#subsetting for study participation at age 16 and 23 (TEDS 21)
data16 = df[df$pcexdata1 == 1, ]
data21a = df[df$u1cdata1 == 1,]
data21 = data21a[data21a$u2cdata1 == 1,]
#compare SES between groups
t.test(data16$SESscore, data21$SESscore, var.equal=T)
##
## Two Sample t-test
##
## data: data16$SESscore and data21$SESscore
## t = -4.2019, df = 9639, p-value = 2.67e-05
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.12353923 -0.04494211
## sample estimates:
## mean of x mean of y
## -0.02942628 0.05481439
# Two Sample t-test <-- SES differs significantly between age 16 and age 23
#
#data: data16$SESscore and data21$SESscore
#t = -4.2019, df = 9639, p-value = 2.67e-05
#alternative hypothesis: true difference in means is not equal to 0
#95 percent confidence interval:
# -0.12353923 -0.04494211
#sample estimates:
# mean of x mean of y
#-0.02942628 0.05481439
#Step 3: #Regression models without moderation
IV: Zgcse DVs: linear: Zhqual, Zdegree, Zsoc, Zinc, Zmon, Zfina, Zwellb, Zanx, Zsdq, Zalc logistic: u1cbenf11, status_bin multi-nomial: status1
Model 1: DV ~ sex1 + SESscore Model 2: DV ~ sex1 + SESscore + Zgcse Model 3: DV ~ sex1 + SESscore + Zgcse + Zhqual
#linear regressions (w/o mod)
rm(list=ls())
ls()
## character(0)
#read in random1-dataset with only non-missing GCSE information
df <- read.csv("/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_random1.csv", header = T, strip.white = T,na.strings = c('NA', '', ' '
))
model1.hqual <- 'Zhqual ~ sex1 + SESscore'
model1.hqualfit <- sem(model1.hqual, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.hqualfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 448.950
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18296.800
## Loglikelihood unrestricted model (H1) -18296.800
##
## Akaike (AIC) 36611.599
## Bayesian (BIC) 36672.598
## Sample-size adjusted Bayesian (SABIC) 36643.999
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 -0.051 0.032 -1.586 0.113 -0.113 0.012
## SESscore 0.367 0.017 21.898 0.000 0.334 0.399
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.281 0.023 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.002 0.020 -0.119 0.905 -0.041 0.036
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.030 0.012 -2.566 0.010 -0.053 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.883 0.021 42.874 0.000 0.843 0.924
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.380 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zhqual 0.117
standardizedsolution(model1.hqualfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.025 0.016 -1.587 0.112 -0.056 0.006
## 2 Zhqual ~ SESscore 0.342 0.015 23.582 0.000 0.314 0.371
## 3 Zhqual ~~ Zhqual 0.883 0.010 88.748 0.000 0.863 0.902
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.284 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zhqual ~1 -0.002 0.020 -0.119 0.905 -0.041 0.036
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.565 0.010 -0.057 -0.008
model2.hqual <- 'Zhqual ~ sex1 + SESscore + Zgcse'
model2.hqualfit <- sem(model2.hqual, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.hqualfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1271.097
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26253.556
## Loglikelihood unrestricted model (H1) -26253.556
##
## Akaike (AIC) 52535.111
## Bayesian (BIC) 52629.999
## Sample-size adjusted Bayesian (SABIC) 52585.511
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 -0.038 0.029 -1.319 0.187 -0.093 0.018
## SESscore 0.133 0.017 7.900 0.000 0.100 0.167
## Zgcse 0.504 0.017 30.177 0.000 0.472 0.537
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.099 0.018 -5.485 0.000 -0.134 -0.063
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.708 0.016 42.936 0.000 0.676 0.740
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.319
standardizedsolution(model2.hqualfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.018 0.014 -1.320 0.187 -0.046 0.009
## 2 Zhqual ~ SESscore 0.122 0.015 7.937 0.000 0.092 0.153
## 3 Zhqual ~ Zgcse 0.495 0.014 34.629 0.000 0.467 0.523
## 4 Zhqual ~~ Zhqual 0.681 0.013 53.043 0.000 0.656 0.706
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.433 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.330 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zhqual ~1 -0.097 0.018 -5.501 0.000 -0.131 -0.062
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.927 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
#get change in R2 for model1 vs. model2, thus the variance explained incrementally by GCSE
(PE.model2.hqual <- parameterEstimates(model2.hqualfit, rsquare = TRUE)) # the R-squared values are in rows where "op" is "r2"
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.038 0.029 -1.319 0.187 -0.093 0.018
## 2 Zhqual ~ SESscore 0.133 0.017 7.900 0.000 0.100 0.167
## 3 Zhqual ~ Zgcse 0.504 0.017 30.177 0.000 0.472 0.537
## 4 Zhqual ~~ Zhqual 0.708 0.016 42.936 0.000 0.676 0.740
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zhqual ~1 -0.099 0.018 -5.485 0.000 -0.134 -0.063
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.928 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zhqual r2 Zhqual 0.319 NA NA NA NA NA
PE.model2.hqual$est[PE.model2.hqual$op == "r2"]
## [1] 0.3187157
(PE.model1.hqual <- parameterEstimates(model1.hqualfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.051 0.032 -1.586 0.113 -0.113 0.012
## 2 Zhqual ~ SESscore 0.367 0.017 21.898 0.000 0.334 0.399
## 3 Zhqual ~~ Zhqual 0.883 0.021 42.874 0.000 0.843 0.924
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.281 0.023 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.380 0.000 0.842 0.903
## 7 Zhqual ~1 -0.002 0.020 -0.119 0.905 -0.041 0.036
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.030 0.012 -2.566 0.010 -0.053 -0.007
## 10 Zhqual r2 Zhqual 0.117 NA NA NA NA NA
PE.model1.hqual$est[PE.model1.hqual$op == "r2"]
## [1] 0.1172887
r2diff2.hqual <- (PE.model2.hqual$est[PE.model2.hqual$op == "r2"] - PE.model1.hqual$est[PE.model1.hqual$op == "r2"])
print(r2diff2.hqual) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.2014269
model1.degree <- 'Zdegree ~ sex1 + SESscore'
model1.degreefit <- sem(model1.degree, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.degreefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 26.403
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -15792.225
## Loglikelihood unrestricted model (H1) -15792.225
##
## Akaike (AIC) 31602.450
## Bayesian (BIC) 31663.449
## Sample-size adjusted Bayesian (SABIC) 31634.850
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 -0.056 0.049 -1.138 0.255 -0.153 0.040
## SESscore 0.138 0.027 5.095 0.000 0.085 0.192
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.291 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.011 0.030 -0.374 0.708 -0.070 0.047
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.030 0.012 -2.520 0.012 -0.052 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.984 0.033 29.785 0.000 0.920 1.049
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.386 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zdegree 0.017
standardizedsolution(model1.degreefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.028 0.025 -1.139 0.255 -0.076 0.020
## 2 Zdegree ~ SESscore 0.129 0.025 5.157 0.000 0.080 0.178
## 3 Zdegree ~~ Zdegree 0.983 0.007 148.601 0.000 0.970 0.996
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.294 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zdegree ~1 -0.011 0.030 -0.374 0.708 -0.070 0.047
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.520 0.012 -0.056 -0.007
model2.degree <- 'Zdegree ~ sex1 + SESscore + Zgcse'
model2.degreefit <- sem(model2.degree, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.degreefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 152.079
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -24097.216
## Loglikelihood unrestricted model (H1) -24097.216
##
## Akaike (AIC) 48222.432
## Bayesian (BIC) 48317.320
## Sample-size adjusted Bayesian (SABIC) 48272.832
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 -0.080 0.048 -1.673 0.094 -0.173 0.014
## SESscore 0.014 0.028 0.506 0.613 -0.041 0.070
## Zgcse 0.375 0.033 11.366 0.000 0.310 0.439
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.433 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.233 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.170 0.032 -5.308 0.000 -0.232 -0.107
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.917 0.031 29.791 0.000 0.857 0.978
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.957 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.139
standardizedsolution(model2.degreefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.038 0.023 -1.678 0.093 -0.083 0.006
## 2 Zdegree ~ SESscore 0.013 0.026 0.506 0.613 -0.037 0.064
## 3 Zdegree ~ Zgcse 0.363 0.029 12.537 0.000 0.306 0.420
## 4 Zdegree ~~ Zdegree 0.861 0.020 43.925 0.000 0.822 0.899
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.436 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.251 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.349 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zdegree ~1 -0.164 0.030 -5.408 0.000 -0.224 -0.105
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.928 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
#get change in R2 for model1 vs. model2, thus the variance explained incrementally by GCSE
(PE.model2.degree <- parameterEstimates(model2.degreefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.080 0.048 -1.673 0.094 -0.173 0.014
## 2 Zdegree ~ SESscore 0.014 0.028 0.506 0.613 -0.041 0.070
## 3 Zdegree ~ Zgcse 0.375 0.033 11.366 0.000 0.310 0.439
## 4 Zdegree ~~ Zdegree 0.917 0.031 29.791 0.000 0.857 0.978
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.433 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.233 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.957 0.000 0.965 1.034
## 11 Zdegree ~1 -0.170 0.032 -5.308 0.000 -0.232 -0.107
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.928 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zdegree r2 Zdegree 0.139 NA NA NA NA NA
PE.model2.degree$est[PE.model2.degree$op == "r2"]
## [1] 0.1393086
(PE.model1.degree <- parameterEstimates(model1.degreefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.056 0.049 -1.138 0.255 -0.153 0.040
## 2 Zdegree ~ SESscore 0.138 0.027 5.095 0.000 0.085 0.192
## 3 Zdegree ~~ Zdegree 0.984 0.033 29.785 0.000 0.920 1.049
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.291 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.386 0.000 0.842 0.903
## 7 Zdegree ~1 -0.011 0.030 -0.374 0.708 -0.070 0.047
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.030 0.012 -2.520 0.012 -0.052 -0.007
## 10 Zdegree r2 Zdegree 0.017 NA NA NA NA NA
PE.model1.degree$est[PE.model1.degree$op == "r2"]
## [1] 0.01726796
r2diff2.degree <- (PE.model2.degree$est[PE.model2.degree$op == "r2"] - PE.model1.degree$est[PE.model1.degree$op == "r2"])
print(r2diff2.degree) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.1220407
model1.ocprestige <- 'Zsoc ~ sex1 + SESscore'
model1.ocprestigefit <- sem(model1.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 64.154
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -15647.064
## Loglikelihood unrestricted model (H1) -15647.064
##
## Akaike (AIC) 31312.128
## Bayesian (BIC) 31373.127
## Sample-size adjusted Bayesian (SABIC) 31344.527
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.156 0.050 3.128 0.002 0.058 0.253
## SESscore 0.197 0.027 7.361 0.000 0.144 0.249
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.291 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc -0.026 0.030 -0.854 0.393 -0.085 0.033
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.030 0.012 -2.538 0.011 -0.053 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.962 0.033 29.022 0.000 0.897 1.027
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.387 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zsoc 0.041
standardizedsolution(model1.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.078 0.025 3.141 0.002 0.029 0.126
## 2 Zsoc ~ SESscore 0.184 0.024 7.538 0.000 0.136 0.231
## 3 Zsoc ~~ Zsoc 0.959 0.010 98.554 0.000 0.940 0.979
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.294 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zsoc ~1 -0.026 0.030 -0.854 0.393 -0.085 0.033
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.537 0.011 -0.056 -0.007
model2.ocprestige <- 'Zsoc ~ sex1 + SESscore + Zgcse'
model2.ocprestigefit <- sem(model2.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 165.717
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23964.112
## Loglikelihood unrestricted model (H1) -23964.112
##
## Akaike (AIC) 47956.223
## Bayesian (BIC) 48051.111
## Sample-size adjusted Bayesian (SABIC) 48006.623
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.163 0.048 3.385 0.001 0.069 0.258
## SESscore 0.069 0.029 2.407 0.016 0.013 0.126
## Zgcse 0.286 0.028 10.148 0.000 0.231 0.342
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.433 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc -0.042 0.029 -1.422 0.155 -0.099 0.016
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.931 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.906 0.031 29.033 0.000 0.845 0.967
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zsoc 0.107
standardizedsolution(model2.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.081 0.024 3.396 0.001 0.034 0.128
## 2 Zsoc ~ SESscore 0.065 0.027 2.413 0.016 0.012 0.117
## 3 Zsoc ~ Zgcse 0.284 0.027 10.644 0.000 0.232 0.337
## 4 Zsoc ~~ Zsoc 0.893 0.015 59.622 0.000 0.864 0.922
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.436 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.350 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zsoc ~1 -0.042 0.029 -1.423 0.155 -0.099 0.016
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.930 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.ocprestige <- 'Zsoc ~ sex1 + SESscore + Zgcse + Zhqual'
model3.ocprestigefit <- sem(model3.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 208.800
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -28540.986
## Loglikelihood unrestricted model (H1) -28540.986
##
## Akaike (AIC) 57121.972
## Bayesian (BIC) 57257.526
## Sample-size adjusted Bayesian (SABIC) 57193.971
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.183 0.048 3.824 0.000 0.089 0.276
## SESscore 0.046 0.029 1.606 0.108 -0.010 0.102
## Zgcse 0.191 0.031 6.066 0.000 0.129 0.252
## Zhqual 0.168 0.025 6.601 0.000 0.118 0.218
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.428 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.610 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.301 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.575 0.000 0.530 0.601
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc -0.000 0.030 -0.003 0.998 -0.058 0.058
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.930 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.531 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.883 0.030 29.022 0.000 0.823 0.942
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.563 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zsoc 0.122
standardizedsolution(model3.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.091 0.024 3.841 0.000 0.045 0.137
## 2 Zsoc ~ SESscore 0.043 0.027 1.608 0.108 -0.009 0.095
## 3 Zsoc ~ Zgcse 0.190 0.031 6.184 0.000 0.130 0.250
## 4 Zsoc ~ Zhqual 0.171 0.026 6.649 0.000 0.120 0.221
## 5 Zsoc ~~ Zsoc 0.878 0.015 58.145 0.000 0.849 0.908
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.432 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.618 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.332 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.359 0.014 26.420 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.555 0.012 47.947 0.000 0.532 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zsoc ~1 0.000 0.030 -0.003 0.998 -0.058 0.058
## 17 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.929 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.597 0.000 -0.150 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.ocprestige <- parameterEstimates(model3.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.183 0.048 3.824 0.000 0.089 0.276
## 2 Zsoc ~ SESscore 0.046 0.029 1.606 0.108 -0.010 0.102
## 3 Zsoc ~ Zgcse 0.191 0.031 6.066 0.000 0.129 0.252
## 4 Zsoc ~ Zhqual 0.168 0.025 6.601 0.000 0.118 0.218
## 5 Zsoc ~~ Zsoc 0.883 0.030 29.022 0.000 0.823 0.942
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.428 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.610 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.301 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.575 0.000 0.530 0.601
## 15 Zhqual ~~ Zhqual 1.040 0.024 42.563 0.000 0.992 1.088
## 16 Zsoc ~1 0.000 0.030 -0.003 0.998 -0.058 0.058
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.930 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.531 0.000 -0.153 -0.090
## 21 Zsoc r2 Zsoc 0.122 NA NA NA NA NA
PE.model3.ocprestige$est[PE.model3.ocprestige$op == "r2"]
## [1] 0.1216973
(PE.model2.ocprestige <- parameterEstimates(model2.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.163 0.048 3.385 0.001 0.069 0.258
## 2 Zsoc ~ SESscore 0.069 0.029 2.407 0.016 0.013 0.126
## 3 Zsoc ~ Zgcse 0.286 0.028 10.148 0.000 0.231 0.342
## 4 Zsoc ~~ Zsoc 0.906 0.031 29.033 0.000 0.845 0.967
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.433 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zsoc ~1 -0.042 0.029 -1.422 0.155 -0.099 0.016
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.931 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zsoc r2 Zsoc 0.107 NA NA NA NA NA
PE.model2.ocprestige$est[PE.model2.ocprestige$op == "r2"]
## [1] 0.1070241
(PE.model1.ocprestige <- parameterEstimates(model1.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.156 0.050 3.128 0.002 0.058 0.253
## 2 Zsoc ~ SESscore 0.197 0.027 7.361 0.000 0.144 0.249
## 3 Zsoc ~~ Zsoc 0.962 0.033 29.022 0.000 0.897 1.027
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.291 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.387 0.000 0.842 0.903
## 7 Zsoc ~1 -0.026 0.030 -0.854 0.393 -0.085 0.033
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.030 0.012 -2.538 0.011 -0.053 -0.007
## 10 Zsoc r2 Zsoc 0.041 NA NA NA NA NA
PE.model1.ocprestige$est[PE.model1.ocprestige$op == "r2"]
## [1] 0.04052599
r2diff2.ocprestige <- (PE.model2.ocprestige$est[PE.model2.ocprestige$op == "r2"] - PE.model1.ocprestige$est[PE.model1.ocprestige$op == "r2"])
print(r2diff2.ocprestige) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.06649815
r2diff3.ocprestige <- (PE.model3.ocprestige$est[PE.model3.ocprestige$op == "r2"] - PE.model2.ocprestige$est[PE.model2.ocprestige$op == "r2"])
print(r2diff3.ocprestige) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.01467316
model1.inc <- 'Zinc ~ sex1 + SESscore'
model1.incfit <- sem(model1.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 91.241
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -15910.213
## Loglikelihood unrestricted model (H1) -15910.213
##
## Akaike (AIC) 31838.427
## Bayesian (BIC) 31899.426
## Sample-size adjusted Bayesian (SABIC) 31870.826
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.385 0.047 8.197 0.000 0.293 0.477
## SESscore 0.123 0.025 4.895 0.000 0.074 0.172
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.286 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.120 0.028 -4.246 0.000 -0.176 -0.065
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.030 0.012 -2.525 0.012 -0.053 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.952 0.031 30.663 0.000 0.891 1.013
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.388 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zinc 0.051
standardizedsolution(model1.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.192 0.023 8.413 0.000 0.147 0.236
## 2 Zinc ~ SESscore 0.115 0.023 4.939 0.000 0.069 0.160
## 3 Zinc ~~ Zinc 0.949 0.010 92.864 0.000 0.929 0.969
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.289 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zinc ~1 -0.120 0.028 -4.278 0.000 -0.175 -0.065
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.525 0.012 -0.056 -0.007
model2.inc <- 'Zinc ~ sex1 + SESscore + Zgcse'
model2.incfit <- sem(model2.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 22 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 133.447
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -24256.940
## Loglikelihood unrestricted model (H1) -24256.940
##
## Akaike (AIC) 48541.879
## Bayesian (BIC) 48636.767
## Sample-size adjusted Bayesian (SABIC) 48592.279
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.386 0.046 8.315 0.000 0.295 0.477
## SESscore 0.044 0.028 1.590 0.112 -0.010 0.098
## Zgcse 0.173 0.027 6.504 0.000 0.121 0.225
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.432 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.126 0.028 -4.475 0.000 -0.181 -0.071
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.930 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.931 0.030 30.667 0.000 0.871 0.991
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zinc 0.072
standardizedsolution(model2.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.192 0.023 8.515 0.000 0.148 0.237
## 2 Zinc ~ SESscore 0.041 0.026 1.592 0.111 -0.010 0.092
## 3 Zinc ~ Zgcse 0.173 0.026 6.603 0.000 0.122 0.224
## 4 Zinc ~~ Zinc 0.928 0.012 79.277 0.000 0.905 0.951
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.436 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.347 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zinc ~1 -0.125 0.028 -4.508 0.000 -0.180 -0.071
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.929 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.inc <- 'Zinc ~ sex1 + SESscore + Zgcse + Zhqual'
model3.incfit <- sem(model3.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 134.088
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -28855.035
## Loglikelihood unrestricted model (H1) -28855.035
##
## Akaike (AIC) 57750.069
## Bayesian (BIC) 57885.624
## Sample-size adjusted Bayesian (SABIC) 57822.069
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.388 0.046 8.350 0.000 0.297 0.479
## SESscore 0.041 0.028 1.482 0.138 -0.013 0.096
## Zgcse 0.162 0.030 5.404 0.000 0.103 0.221
## Zhqual 0.020 0.025 0.802 0.423 -0.029 0.069
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.427 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.607 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.279 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.552 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.121 0.029 -4.210 0.000 -0.177 -0.065
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.517 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.931 0.030 30.666 0.000 0.871 0.990
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.569 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zinc 0.073
standardizedsolution(model3.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.194 0.023 8.553 0.000 0.149 0.238
## 2 Zinc ~ SESscore 0.039 0.026 1.484 0.138 -0.012 0.090
## 3 Zinc ~ Zgcse 0.162 0.030 5.462 0.000 0.104 0.220
## 4 Zinc ~ Zhqual 0.020 0.025 0.802 0.423 -0.029 0.070
## 5 Zinc ~~ Zinc 0.927 0.012 79.254 0.000 0.904 0.950
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.431 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.616 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.330 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.359 0.014 26.384 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.554 0.012 47.878 0.000 0.532 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zinc ~1 -0.121 0.028 -4.238 0.000 -0.176 -0.065
## 17 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.928 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.582 0.000 -0.149 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.inc <- parameterEstimates(model3.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.388 0.046 8.350 0.000 0.297 0.479
## 2 Zinc ~ SESscore 0.041 0.028 1.482 0.138 -0.013 0.096
## 3 Zinc ~ Zgcse 0.162 0.030 5.404 0.000 0.103 0.221
## 4 Zinc ~ Zhqual 0.020 0.025 0.802 0.423 -0.029 0.069
## 5 Zinc ~~ Zinc 0.931 0.030 30.666 0.000 0.871 0.990
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.427 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.607 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.279 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.552 0.000 0.530 0.600
## 15 Zhqual ~~ Zhqual 1.040 0.024 42.569 0.000 0.992 1.087
## 16 Zinc ~1 -0.121 0.029 -4.210 0.000 -0.177 -0.065
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.929 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.517 0.000 -0.153 -0.089
## 21 Zinc r2 Zinc 0.073 NA NA NA NA NA
PE.model3.inc$est[PE.model3.inc$op == "r2"]
## [1] 0.07256701
(PE.model2.inc <- parameterEstimates(model2.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.386 0.046 8.315 0.000 0.295 0.477
## 2 Zinc ~ SESscore 0.044 0.028 1.590 0.112 -0.010 0.098
## 3 Zinc ~ Zgcse 0.173 0.027 6.504 0.000 0.121 0.225
## 4 Zinc ~~ Zinc 0.931 0.030 30.667 0.000 0.871 0.991
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.432 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zinc ~1 -0.126 0.028 -4.475 0.000 -0.181 -0.071
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.930 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zinc r2 Zinc 0.072 NA NA NA NA NA
PE.model2.inc$est[PE.model2.inc$op == "r2"]
## [1] 0.07238421
(PE.model1.inc <- parameterEstimates(model1.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.385 0.047 8.197 0.000 0.293 0.477
## 2 Zinc ~ SESscore 0.123 0.025 4.895 0.000 0.074 0.172
## 3 Zinc ~~ Zinc 0.952 0.031 30.663 0.000 0.891 1.013
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.286 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.388 0.000 0.842 0.903
## 7 Zinc ~1 -0.120 0.028 -4.246 0.000 -0.176 -0.065
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.030 0.012 -2.525 0.012 -0.053 -0.007
## 10 Zinc r2 Zinc 0.051 NA NA NA NA NA
PE.model1.inc$est[PE.model1.inc$op == "r2"]
## [1] 0.05123494
r2diff2.inc <- (PE.model2.inc$est[PE.model2.inc$op == "r2"] - PE.model1.inc$est[PE.model1.inc$op == "r2"])
print(r2diff2.inc) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.02114927
r2diff3.inc <- (PE.model3.inc$est[PE.model3.inc$op == "r2"] - PE.model2.inc$est[PE.model2.inc$op == "r2"])
print(r2diff3.inc) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.0001827967
model1.mon <- 'Zmon ~ sex1 + SESscore'
model1.monfit <- sem(model1.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 56.036
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18452.108
## Loglikelihood unrestricted model (H1) -18452.108
##
## Akaike (AIC) 36922.215
## Bayesian (BIC) 36983.215
## Sample-size adjusted Bayesian (SABIC) 36954.615
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.232 0.034 -6.887 0.000 -0.298 -0.166
## SESscore -0.047 0.018 -2.652 0.008 -0.082 -0.012
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.288 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.093 0.021 4.422 0.000 0.052 0.134
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.029 0.012 -2.514 0.012 -0.052 -0.006
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.985 0.023 42.777 0.000 0.939 1.030
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.387 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zmon 0.016
standardizedsolution(model1.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.116 0.017 -6.945 0.000 -0.149 -0.083
## 2 Zmon ~ SESscore -0.044 0.017 -2.654 0.008 -0.077 -0.012
## 3 Zmon ~~ Zmon 0.984 0.004 237.936 0.000 0.976 0.992
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.290 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zmon ~1 0.093 0.021 4.441 0.000 0.052 0.133
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.514 0.012 -0.056 -0.007
model2.mon <- 'Zmon ~ sex1 + SESscore + Zgcse'
model2.monfit <- sem(model2.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 78.621
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26808.644
## Loglikelihood unrestricted model (H1) -26808.644
##
## Akaike (AIC) 53645.288
## Bayesian (BIC) 53740.176
## Sample-size adjusted Bayesian (SABIC) 53695.688
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.230 0.034 -6.850 0.000 -0.296 -0.164
## SESscore -0.090 0.020 -4.476 0.000 -0.129 -0.051
## Zgcse 0.096 0.020 4.866 0.000 0.057 0.134
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.431 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.428 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.075 0.021 3.519 0.000 0.033 0.116
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.925 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.978 0.023 42.774 0.000 0.934 1.023
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.321 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zmon 0.023
standardizedsolution(model2.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.115 0.017 -6.911 0.000 -0.148 -0.082
## 2 Zmon ~ SESscore -0.084 0.019 -4.491 0.000 -0.121 -0.047
## 3 Zmon ~ Zgcse 0.095 0.020 4.890 0.000 0.057 0.134
## 4 Zmon ~~ Zmon 0.977 0.005 188.026 0.000 0.966 0.987
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.434 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.317 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zmon ~1 0.075 0.021 3.528 0.000 0.033 0.116
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.924 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.mon <- 'Zmon ~ sex1 + SESscore + Zgcse + Zhqual'
model3.monfit <- sem(model3.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 80.248
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -31406.247
## Loglikelihood unrestricted model (H1) -31406.247
##
## Akaike (AIC) 62852.494
## Bayesian (BIC) 62988.048
## Sample-size adjusted Bayesian (SABIC) 62924.493
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.230 0.034 -6.828 0.000 -0.295 -0.164
## SESscore -0.093 0.020 -4.613 0.000 -0.133 -0.054
## Zgcse 0.084 0.022 3.807 0.000 0.041 0.127
## Zhqual 0.024 0.020 1.208 0.227 -0.015 0.062
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.603 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.423 0.000 0.422 0.472
## Zhqual 0.342 0.015 22.278 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.554 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.077 0.021 3.618 0.000 0.035 0.119
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.924 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.517 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.978 0.023 42.774 0.000 0.933 1.023
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.874 0.016 56.325 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.571 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zmon 0.024
standardizedsolution(model3.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.115 0.017 -6.888 0.000 -0.147 -0.082
## 2 Zmon ~ SESscore -0.087 0.019 -4.630 0.000 -0.124 -0.050
## 3 Zmon ~ Zgcse 0.084 0.022 3.819 0.000 0.041 0.127
## 4 Zmon ~ Zhqual 0.024 0.020 1.209 0.227 -0.015 0.063
## 5 Zmon ~~ Zmon 0.976 0.005 186.320 0.000 0.966 0.986
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.429 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.612 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.299 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.359 0.014 26.383 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.554 0.012 47.880 0.000 0.532 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zmon ~1 0.077 0.021 3.628 0.000 0.035 0.119
## 17 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.924 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.582 0.000 -0.149 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.mon <- parameterEstimates(model3.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.230 0.034 -6.828 0.000 -0.295 -0.164
## 2 Zmon ~ SESscore -0.093 0.020 -4.613 0.000 -0.133 -0.054
## 3 Zmon ~ Zgcse 0.084 0.022 3.807 0.000 0.041 0.127
## 4 Zmon ~ Zhqual 0.024 0.020 1.208 0.227 -0.015 0.062
## 5 Zmon ~~ Zmon 0.978 0.023 42.774 0.000 0.933 1.023
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.603 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.874 0.016 56.325 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.423 0.000 0.422 0.472
## 12 SESscore ~~ Zhqual 0.342 0.015 22.278 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.554 0.000 0.530 0.600
## 15 Zhqual ~~ Zhqual 1.040 0.024 42.571 0.000 0.992 1.087
## 16 Zmon ~1 0.077 0.021 3.618 0.000 0.035 0.119
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.924 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.517 0.000 -0.153 -0.089
## 21 Zmon r2 Zmon 0.024 NA NA NA NA NA
PE.model3.mon$est[PE.model3.mon$op == "r2"]
## [1] 0.02390799
(PE.model2.mon <- parameterEstimates(model2.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.230 0.034 -6.850 0.000 -0.296 -0.164
## 2 Zmon ~ SESscore -0.090 0.020 -4.476 0.000 -0.129 -0.051
## 3 Zmon ~ Zgcse 0.096 0.020 4.866 0.000 0.057 0.134
## 4 Zmon ~~ Zmon 0.978 0.023 42.774 0.000 0.934 1.023
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.431 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.321 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.428 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zmon ~1 0.075 0.021 3.519 0.000 0.033 0.116
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.925 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zmon r2 Zmon 0.023 NA NA NA NA NA
PE.model2.mon$est[PE.model2.mon$op == "r2"]
## [1] 0.0234538
(PE.model1.mon <- parameterEstimates(model1.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.232 0.034 -6.887 0.000 -0.298 -0.166
## 2 Zmon ~ SESscore -0.047 0.018 -2.652 0.008 -0.082 -0.012
## 3 Zmon ~~ Zmon 0.985 0.023 42.777 0.000 0.939 1.030
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.288 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.387 0.000 0.842 0.903
## 7 Zmon ~1 0.093 0.021 4.422 0.000 0.052 0.134
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.029 0.012 -2.514 0.012 -0.052 -0.006
## 10 Zmon r2 Zmon 0.016 NA NA NA NA NA
PE.model1.mon$est[PE.model1.mon$op == "r2"]
## [1] 0.01569144
r2diff2.mon <- (PE.model2.mon$est[PE.model2.mon$op == "r2"] - PE.model1.mon$est[PE.model1.mon$op == "r2"])
print(r2diff2.mon) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.007762354
r2diff3.mon <- (PE.model3.mon$est[PE.model3.mon$op == "r2"] - PE.model2.mon$est[PE.model2.mon$op == "r2"])
print(r2diff3.mon) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.0004541953
model1.fina <- 'Zfina ~ sex1 + SESscore'
model1.finafit <- sem(model1.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 14.266
## Degrees of freedom 2
## P-value 0.001
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18475.831
## Loglikelihood unrestricted model (H1) -18475.831
##
## Akaike (AIC) 36969.661
## Bayesian (BIC) 37030.661
## Sample-size adjusted Bayesian (SABIC) 37002.061
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.065 0.034 1.909 0.056 -0.002 0.131
## SESscore -0.060 0.018 -3.357 0.001 -0.095 -0.025
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.285 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.021 0.021 -1.015 0.310 -0.063 0.020
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.029 0.012 -2.506 0.012 -0.052 -0.006
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.996 0.023 42.788 0.000 0.950 1.041
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.387 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zfina 0.004
standardizedsolution(model1.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.032 0.017 1.910 0.056 -0.001 0.066
## 2 Zfina ~ SESscore -0.056 0.017 -3.364 0.001 -0.089 -0.023
## 3 Zfina ~~ Zfina 0.996 0.002 461.108 0.000 0.992 1.000
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.288 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zfina ~1 -0.021 0.021 -1.015 0.310 -0.063 0.020
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 SESscore ~1 -0.031 0.013 -2.505 0.012 -0.056 -0.007
model2.fina <- 'Zfina ~ sex1 + SESscore + Zgcse'
model2.finafit <- sem(model2.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 18.258
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26841.664
## Loglikelihood unrestricted model (H1) -26841.664
##
## Akaike (AIC) 53711.327
## Bayesian (BIC) 53806.215
## Sample-size adjusted Bayesian (SABIC) 53761.727
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.066 0.034 1.933 0.053 -0.001 0.132
## SESscore -0.079 0.020 -3.887 0.000 -0.118 -0.039
## Zgcse 0.044 0.020 2.202 0.028 0.005 0.082
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.431 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.030 0.021 -1.389 0.165 -0.072 0.012
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.916 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.995 0.023 42.787 0.000 0.949 1.040
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zfina 0.005
standardizedsolution(model2.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.033 0.017 1.934 0.053 0.000 0.066
## 2 Zfina ~ SESscore -0.074 0.019 -3.897 0.000 -0.111 -0.037
## 3 Zfina ~ Zgcse 0.044 0.020 2.204 0.028 0.005 0.082
## 4 Zfina ~~ Zfina 0.995 0.002 424.388 0.000 0.990 1.000
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.433 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.329 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zfina ~1 -0.030 0.021 -1.390 0.165 -0.072 0.012
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 SESscore ~1 -0.036 0.013 -2.916 0.004 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.fina <- 'Zfina ~ sex1 + SESscore + Zgcse + Zhqual'
model3.finafit <- sem(model3.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 34.517
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -31431.950
## Loglikelihood unrestricted model (H1) -31431.950
##
## Akaike (AIC) 62903.900
## Bayesian (BIC) 63039.454
## Sample-size adjusted Bayesian (SABIC) 62975.899
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.063 0.034 1.863 0.062 -0.003 0.129
## SESscore -0.069 0.020 -3.376 0.001 -0.109 -0.029
## Zgcse 0.084 0.022 3.788 0.000 0.040 0.127
## Zhqual -0.079 0.020 -4.007 0.000 -0.118 -0.040
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.425 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.595 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.428 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.274 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.549 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.038 0.021 -1.768 0.077 -0.080 0.004
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.918 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.527 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.990 0.023 42.784 0.000 0.945 1.036
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.321 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.579 0.000 0.991 1.087
##
## R-Square:
## Estimate
## Zfina 0.010
standardizedsolution(model3.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.031 0.017 1.864 0.062 -0.002 0.065
## 2 Zfina ~ SESscore -0.064 0.019 -3.382 0.001 -0.102 -0.027
## 3 Zfina ~ Zgcse 0.084 0.022 3.797 0.000 0.041 0.127
## 4 Zfina ~ Zhqual -0.081 0.020 -4.016 0.000 -0.120 -0.041
## 5 Zfina ~~ Zfina 0.990 0.003 307.110 0.000 0.984 0.997
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.428 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.603 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.315 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.358 0.014 26.375 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.554 0.012 47.858 0.000 0.531 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zfina ~1 -0.038 0.021 -1.769 0.077 -0.080 0.004
## 17 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.917 0.004 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.593 0.000 -0.150 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.fina <- parameterEstimates(model3.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.063 0.034 1.863 0.062 -0.003 0.129
## 2 Zfina ~ SESscore -0.069 0.020 -3.376 0.001 -0.109 -0.029
## 3 Zfina ~ Zgcse 0.084 0.022 3.788 0.000 0.040 0.127
## 4 Zfina ~ Zhqual -0.079 0.020 -4.007 0.000 -0.118 -0.040
## 5 Zfina ~~ Zfina 0.990 0.023 42.784 0.000 0.945 1.036
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.425 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.595 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.321 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.428 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.274 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.549 0.000 0.530 0.600
## 15 Zhqual ~~ Zhqual 1.039 0.024 42.579 0.000 0.991 1.087
## 16 Zfina ~1 -0.038 0.021 -1.768 0.077 -0.080 0.004
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.918 0.004 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.527 0.000 -0.153 -0.090
## 21 Zfina r2 Zfina 0.010 NA NA NA NA NA
PE.model3.fina$est[PE.model3.fina$op == "r2"]
## [1] 0.009545627
(PE.model2.fina <- parameterEstimates(model2.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.066 0.034 1.933 0.053 -0.001 0.132
## 2 Zfina ~ SESscore -0.079 0.020 -3.887 0.000 -0.118 -0.039
## 3 Zfina ~ Zgcse 0.044 0.020 2.202 0.028 0.005 0.082
## 4 Zfina ~~ Zfina 0.995 0.023 42.787 0.000 0.949 1.040
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.431 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zfina ~1 -0.030 0.021 -1.389 0.165 -0.072 0.012
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.916 0.004 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zfina r2 Zfina 0.005 NA NA NA NA NA
PE.model2.fina$est[PE.model2.fina$op == "r2"]
## [1] 0.005030792
(PE.model1.fina <- parameterEstimates(model1.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.065 0.034 1.909 0.056 -0.002 0.131
## 2 Zfina ~ SESscore -0.060 0.018 -3.357 0.001 -0.095 -0.025
## 3 Zfina ~~ Zfina 0.996 0.023 42.788 0.000 0.950 1.041
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.285 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.387 0.000 0.842 0.903
## 7 Zfina ~1 -0.021 0.021 -1.015 0.310 -0.063 0.020
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.029 0.012 -2.506 0.012 -0.052 -0.006
## 10 Zfina r2 Zfina 0.004 NA NA NA NA NA
PE.model1.fina$est[PE.model1.fina$op == "r2"]
## [1] 0.004092698
r2diff2.fina <- (PE.model2.fina$est[PE.model2.fina$op == "r2"] - PE.model1.fina$est[PE.model1.fina$op == "r2"])
print(r2diff2.fina) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.0009380946
r2diff3.fina <- (PE.model3.fina$est[PE.model3.fina$op == "r2"] - PE.model2.fina$est[PE.model2.fina$op == "r2"])
print(r2diff3.fina) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.004514834
model1.wellb <- 'Zwellb ~ sex1 + SESscore'
model1.wellbfit <- sem(model1.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 77.198
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18574.907
## Loglikelihood unrestricted model (H1) -18574.907
##
## Akaike (AIC) 37167.813
## Bayesian (BIC) 37228.813
## Sample-size adjusted Bayesian (SABIC) 37200.213
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.261 0.033 7.851 0.000 0.196 0.326
## SESscore 0.064 0.017 3.653 0.000 0.030 0.098
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.299 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.104 0.021 -5.042 0.000 -0.144 -0.063
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.030 0.012 -2.524 0.012 -0.053 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.979 0.023 43.322 0.000 0.935 1.024
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.386 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zwellb 0.021
standardizedsolution(model1.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.130 0.016 7.934 0.000 0.098 0.163
## 2 Zwellb ~ SESscore 0.060 0.016 3.660 0.000 0.028 0.091
## 3 Zwellb ~~ Zwellb 0.979 0.005 208.510 0.000 0.970 0.988
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.302 0.021 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zwellb ~1 -0.104 0.020 -5.068 0.000 -0.144 -0.064
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.524 0.012 -0.056 -0.007
model2.wellb <- 'Zwellb ~ sex1 + SESscore + Zgcse'
model2.wellbfit <- sem(model2.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 109.853
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26926.409
## Loglikelihood unrestricted model (H1) -26926.409
##
## Akaike (AIC) 53880.818
## Bayesian (BIC) 53975.706
## Sample-size adjusted Bayesian (SABIC) 53931.217
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.264 0.033 7.962 0.000 0.199 0.329
## SESscore 0.013 0.020 0.669 0.503 -0.025 0.052
## Zgcse 0.109 0.019 5.644 0.000 0.071 0.147
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.436 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.124 0.021 -5.946 0.000 -0.164 -0.083
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.971 0.022 43.324 0.000 0.927 1.015
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.311 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zwellb 0.029
standardizedsolution(model2.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.132 0.016 8.041 0.000 0.100 0.164
## 2 Zwellb ~ SESscore 0.012 0.018 0.669 0.503 -0.024 0.048
## 3 Zwellb ~ Zgcse 0.109 0.019 5.674 0.000 0.071 0.147
## 4 Zwellb ~~ Zwellb 0.971 0.005 178.297 0.000 0.960 0.981
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.439 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.349 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zwellb ~1 -0.124 0.021 -5.987 0.000 -0.164 -0.083
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.928 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.wellb <- 'Zwellb ~ sex1 + SESscore + Zgcse + Zhqual'
model3.wellbfit <- sem(model3.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 115.841
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -31521.830
## Loglikelihood unrestricted model (H1) -31521.830
##
## Akaike (AIC) 63083.661
## Bayesian (BIC) 63219.215
## Sample-size adjusted Bayesian (SABIC) 63155.660
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.266 0.033 8.034 0.000 0.201 0.331
## SESscore 0.006 0.020 0.316 0.752 -0.033 0.045
## Zgcse 0.085 0.022 3.953 0.000 0.043 0.128
## Zhqual 0.048 0.019 2.455 0.014 0.010 0.086
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.600 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.281 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.557 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.119 0.021 -5.712 0.000 -0.160 -0.078
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.523 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.969 0.022 43.322 0.000 0.925 1.013
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.569 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zwellb 0.031
standardizedsolution(model3.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.133 0.016 8.115 0.000 0.101 0.165
## 2 Zwellb ~ SESscore 0.006 0.019 0.316 0.752 -0.031 0.042
## 3 Zwellb ~ Zgcse 0.085 0.022 3.963 0.000 0.043 0.128
## 4 Zwellb ~ Zhqual 0.049 0.020 2.456 0.014 0.010 0.087
## 5 Zwellb ~~ Zwellb 0.969 0.006 173.064 0.000 0.958 0.980
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.433 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.608 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.332 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.359 0.014 26.387 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.554 0.012 47.893 0.000 0.532 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zwellb ~1 -0.119 0.021 -5.749 0.000 -0.160 -0.078
## 17 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.928 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.588 0.000 -0.149 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.wellb <- parameterEstimates(model3.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.266 0.033 8.034 0.000 0.201 0.331
## 2 Zwellb ~ SESscore 0.006 0.020 0.316 0.752 -0.033 0.045
## 3 Zwellb ~ Zgcse 0.085 0.022 3.953 0.000 0.043 0.128
## 4 Zwellb ~ Zhqual 0.048 0.019 2.455 0.014 0.010 0.086
## 5 Zwellb ~~ Zwellb 0.969 0.022 43.322 0.000 0.925 1.013
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.600 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.281 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.557 0.000 0.530 0.600
## 15 Zhqual ~~ Zhqual 1.040 0.024 42.569 0.000 0.992 1.088
## 16 Zwellb ~1 -0.119 0.021 -5.712 0.000 -0.160 -0.078
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.929 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.523 0.000 -0.153 -0.090
## 21 Zwellb r2 Zwellb 0.031 NA NA NA NA NA
PE.model3.wellb$est[PE.model3.wellb$op == "r2"]
## [1] 0.03093895
(PE.model2.wellb <- parameterEstimates(model2.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.264 0.033 7.962 0.000 0.199 0.329
## 2 Zwellb ~ SESscore 0.013 0.020 0.669 0.503 -0.025 0.052
## 3 Zwellb ~ Zgcse 0.109 0.019 5.644 0.000 0.071 0.147
## 4 Zwellb ~~ Zwellb 0.971 0.022 43.324 0.000 0.927 1.015
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.436 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.311 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zwellb ~1 -0.124 0.021 -5.946 0.000 -0.164 -0.083
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.929 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zwellb r2 Zwellb 0.029 NA NA NA NA NA
PE.model2.wellb$est[PE.model2.wellb$op == "r2"]
## [1] 0.02926232
(PE.model1.wellb <- parameterEstimates(model1.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.261 0.033 7.851 0.000 0.196 0.326
## 2 Zwellb ~ SESscore 0.064 0.017 3.653 0.000 0.030 0.098
## 3 Zwellb ~~ Zwellb 0.979 0.023 43.322 0.000 0.935 1.024
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.299 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.386 0.000 0.842 0.903
## 7 Zwellb ~1 -0.104 0.021 -5.042 0.000 -0.144 -0.063
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.030 0.012 -2.524 0.012 -0.053 -0.007
## 10 Zwellb r2 Zwellb 0.021 NA NA NA NA NA
PE.model1.wellb$est[PE.model1.wellb$op == "r2"]
## [1] 0.0209988
r2diff2.wellb <- (PE.model2.wellb$est[PE.model2.wellb$op == "r2"] - PE.model1.wellb$est[PE.model1.wellb$op == "r2"])
print(r2diff2.wellb) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.008263516
r2diff3.wellb <- (PE.model3.wellb$est[PE.model3.wellb$op == "r2"] - PE.model2.wellb$est[PE.model2.wellb$op == "r2"])
print(r2diff3.wellb) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.001676632
model1.anx <- 'Zanx ~ sex1 + SESscore'
model1.anxfit <- sem(model1.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 90.978
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18106.862
## Loglikelihood unrestricted model (H1) -18106.862
##
## Akaike (AIC) 36231.724
## Bayesian (BIC) 36292.723
## Sample-size adjusted Bayesian (SABIC) 36264.124
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.333 0.035 -9.525 0.000 -0.402 -0.265
## SESscore -0.012 0.018 -0.637 0.524 -0.047 0.024
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.290 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.124 0.021 5.829 0.000 0.082 0.165
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.029 0.012 -2.518 0.012 -0.052 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.974 0.024 41.406 0.000 0.927 1.020
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.387 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zanx 0.028
standardizedsolution(model1.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.166 0.017 -9.697 0.000 -0.200 -0.133
## 2 Zanx ~ SESscore -0.011 0.017 -0.637 0.524 -0.044 0.023
## 3 Zanx ~~ Zanx 0.972 0.006 170.592 0.000 0.961 0.983
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.293 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zanx ~1 0.124 0.021 5.875 0.000 0.082 0.165
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.517 0.012 -0.056 -0.007
model2.anx <- 'Zanx ~ sex1 + SESscore + Zgcse'
model2.anxfit <- sem(model2.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 90.985
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26474.688
## Loglikelihood unrestricted model (H1) -26474.688
##
## Akaike (AIC) 52977.375
## Bayesian (BIC) 53072.263
## Sample-size adjusted Bayesian (SABIC) 53027.775
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.333 0.035 -9.531 0.000 -0.402 -0.265
## SESscore -0.005 0.021 -0.243 0.808 -0.046 0.036
## Zgcse -0.008 0.020 -0.405 0.686 -0.048 0.031
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.434 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.436 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.125 0.022 5.814 0.000 0.083 0.167
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.974 0.024 41.406 0.000 0.927 1.020
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zanx 0.028
standardizedsolution(model2.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.166 0.017 -9.703 0.000 -0.200 -0.133
## 2 Zanx ~ SESscore -0.005 0.019 -0.243 0.808 -0.043 0.033
## 3 Zanx ~ Zgcse -0.008 0.020 -0.405 0.686 -0.048 0.031
## 4 Zanx ~~ Zanx 0.972 0.006 171.014 0.000 0.961 0.983
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.438 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.346 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zanx ~1 0.125 0.021 5.858 0.000 0.083 0.167
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.928 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.anx <- 'Zanx ~ sex1 + SESscore + Zgcse + Zhqual'
model3.anxfit <- sem(model3.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 91.203
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -31072.994
## Loglikelihood unrestricted model (H1) -31072.994
##
## Akaike (AIC) 62185.989
## Bayesian (BIC) 62321.543
## Sample-size adjusted Bayesian (SABIC) 62257.988
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.334 0.035 -9.541 0.000 -0.402 -0.265
## SESscore -0.003 0.021 -0.161 0.872 -0.044 0.038
## Zgcse -0.003 0.023 -0.146 0.884 -0.048 0.041
## Zhqual -0.010 0.021 -0.478 0.633 -0.051 0.031
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.275 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.550 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.124 0.022 5.753 0.000 0.082 0.167
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.515 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.973 0.024 41.406 0.000 0.927 1.020
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.573 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zanx 0.028
standardizedsolution(model3.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.167 0.017 -9.713 0.000 -0.200 -0.133
## 2 Zanx ~ SESscore -0.003 0.020 -0.161 0.872 -0.042 0.035
## 3 Zanx ~ Zgcse -0.003 0.023 -0.146 0.884 -0.048 0.041
## 4 Zanx ~ Zhqual -0.010 0.022 -0.478 0.633 -0.052 0.032
## 5 Zanx ~~ Zanx 0.972 0.006 170.791 0.000 0.961 0.983
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.433 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.613 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.330 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.358 0.014 26.376 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.554 0.012 47.867 0.000 0.531 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zanx ~1 0.124 0.021 5.795 0.000 0.082 0.166
## 17 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.927 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.580 0.000 -0.149 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.anx <- parameterEstimates(model3.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.334 0.035 -9.541 0.000 -0.402 -0.265
## 2 Zanx ~ SESscore -0.003 0.021 -0.161 0.872 -0.044 0.038
## 3 Zanx ~ Zgcse -0.003 0.023 -0.146 0.884 -0.048 0.041
## 4 Zanx ~ Zhqual -0.010 0.021 -0.478 0.633 -0.051 0.031
## 5 Zanx ~~ Zanx 0.973 0.024 41.406 0.000 0.927 1.020
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.275 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.550 0.000 0.530 0.600
## 15 Zhqual ~~ Zhqual 1.039 0.024 42.573 0.000 0.992 1.087
## 16 Zanx ~1 0.124 0.022 5.753 0.000 0.082 0.167
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.928 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.515 0.000 -0.153 -0.089
## 21 Zanx r2 Zanx 0.028 NA NA NA NA NA
PE.model3.anx$est[PE.model3.anx$op == "r2"]
## [1] 0.02776333
(PE.model2.anx <- parameterEstimates(model2.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.333 0.035 -9.531 0.000 -0.402 -0.265
## 2 Zanx ~ SESscore -0.005 0.021 -0.243 0.808 -0.046 0.036
## 3 Zanx ~ Zgcse -0.008 0.020 -0.405 0.686 -0.048 0.031
## 4 Zanx ~~ Zanx 0.974 0.024 41.406 0.000 0.927 1.020
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.434 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.436 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zanx ~1 0.125 0.022 5.814 0.000 0.083 0.167
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.928 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zanx r2 Zanx 0.028 NA NA NA NA NA
PE.model2.anx$est[PE.model2.anx$op == "r2"]
## [1] 0.02769291
(PE.model1.anx <- parameterEstimates(model1.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.333 0.035 -9.525 0.000 -0.402 -0.265
## 2 Zanx ~ SESscore -0.012 0.018 -0.637 0.524 -0.047 0.024
## 3 Zanx ~~ Zanx 0.974 0.024 41.406 0.000 0.927 1.020
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.290 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.387 0.000 0.842 0.903
## 7 Zanx ~1 0.124 0.021 5.829 0.000 0.082 0.165
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.029 0.012 -2.518 0.012 -0.052 -0.007
## 10 Zanx r2 Zanx 0.028 NA NA NA NA NA
PE.model1.anx$est[PE.model1.anx$op == "r2"]
## [1] 0.02784133
r2diff2.anx <- (PE.model2.anx$est[PE.model2.anx$op == "r2"] - PE.model1.anx$est[PE.model1.anx$op == "r2"])
print(r2diff2.anx) #difference model1 vs 2, incremental explained variance by GCSE
## [1] -0.0001484237
r2diff3.anx <- (PE.model3.anx$est[PE.model3.anx$op == "r2"] - PE.model2.anx$est[PE.model2.anx$op == "r2"])
print(r2diff3.anx) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 7.042342e-05
model1.sdq <- 'Zsdq ~ sex1 + SESscore'
model1.sdqfit <- sem(model1.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 86.719
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18571.565
## Loglikelihood unrestricted model (H1) -18571.565
##
## Akaike (AIC) 37161.130
## Bayesian (BIC) 37222.130
## Sample-size adjusted Bayesian (SABIC) 37193.530
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.187 0.033 -5.618 0.000 -0.252 -0.121
## SESscore -0.126 0.017 -7.214 0.000 -0.160 -0.092
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.303 0.021 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.079 0.021 3.831 0.000 0.038 0.119
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.030 0.012 -2.533 0.011 -0.053 -0.007
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.977 0.023 43.317 0.000 0.932 1.021
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.383 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zsdq 0.023
standardizedsolution(model1.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.093 0.016 -5.647 0.000 -0.126 -0.061
## 2 Zsdq ~ SESscore -0.118 0.016 -7.271 0.000 -0.150 -0.086
## 3 Zsdq ~~ Zsdq 0.977 0.005 200.154 0.000 0.967 0.986
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.306 0.021 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zsdq ~1 0.079 0.020 3.842 0.000 0.039 0.119
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.532 0.011 -0.056 -0.007
model2.sdq <- 'Zsdq ~ sex1 + SESscore + Zgcse'
model2.sdqfit <- sem(model2.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 215.457
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26875.026
## Loglikelihood unrestricted model (H1) -26875.026
##
## Akaike (AIC) 53778.051
## Bayesian (BIC) 53872.939
## Sample-size adjusted Bayesian (SABIC) 53828.451
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.192 0.033 -5.874 0.000 -0.256 -0.128
## SESscore -0.024 0.019 -1.253 0.210 -0.063 0.014
## Zgcse -0.216 0.019 -11.322 0.000 -0.253 -0.178
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.436 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.118 0.020 5.758 0.000 0.078 0.158
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.930 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.944 0.022 43.329 0.000 0.901 0.987
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.310 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zsdq 0.059
standardizedsolution(model2.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.096 0.016 -5.899 0.000 -0.127 -0.064
## 2 Zsdq ~ SESscore -0.023 0.018 -1.253 0.210 -0.058 0.013
## 3 Zsdq ~ Zgcse -0.215 0.019 -11.584 0.000 -0.252 -0.179
## 4 Zsdq ~~ Zsdq 0.941 0.008 123.615 0.000 0.926 0.956
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.440 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.352 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zsdq ~1 0.118 0.020 5.792 0.000 0.078 0.158
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.929 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.sdq <- 'Zsdq ~ sex1 + SESscore + Zgcse + Zhqual'
model3.sdqfit <- sem(model3.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 245.717
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -31458.311
## Loglikelihood unrestricted model (H1) -31458.311
##
## Akaike (AIC) 62956.622
## Bayesian (BIC) 63092.176
## Sample-size adjusted Bayesian (SABIC) 63028.622
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.197 0.033 -6.046 0.000 -0.260 -0.133
## SESscore -0.010 0.020 -0.489 0.625 -0.048 0.029
## Zgcse -0.163 0.021 -7.685 0.000 -0.205 -0.122
## Zhqual -0.105 0.019 -5.520 0.000 -0.143 -0.068
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.594 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.287 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.574 0.000 0.530 0.601
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.108 0.020 5.268 0.000 0.068 0.148
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.530 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.936 0.022 43.319 0.000 0.894 0.979
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.565 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zsdq 0.067
standardizedsolution(model3.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.098 0.016 -6.073 0.000 -0.130 -0.066
## 2 Zsdq ~ SESscore -0.009 0.018 -0.489 0.625 -0.045 0.027
## 3 Zsdq ~ Zgcse -0.163 0.021 -7.768 0.000 -0.204 -0.122
## 4 Zsdq ~ Zhqual -0.107 0.019 -5.539 0.000 -0.145 -0.069
## 5 Zsdq ~~ Zsdq 0.933 0.008 115.922 0.000 0.917 0.949
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.433 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.603 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.334 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.359 0.014 26.394 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.555 0.012 47.946 0.000 0.532 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zsdq ~1 0.108 0.020 5.294 0.000 0.068 0.148
## 17 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.928 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.596 0.000 -0.150 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.sdq <- parameterEstimates(model3.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.197 0.033 -6.046 0.000 -0.260 -0.133
## 2 Zsdq ~ SESscore -0.010 0.020 -0.489 0.625 -0.048 0.029
## 3 Zsdq ~ Zgcse -0.163 0.021 -7.685 0.000 -0.205 -0.122
## 4 Zsdq ~ Zhqual -0.105 0.019 -5.520 0.000 -0.143 -0.068
## 5 Zsdq ~~ Zsdq 0.936 0.022 43.319 0.000 0.894 0.979
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.594 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.287 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.574 0.000 0.530 0.601
## 15 Zhqual ~~ Zhqual 1.040 0.024 42.565 0.000 0.992 1.088
## 16 Zsdq ~1 0.108 0.020 5.268 0.000 0.068 0.148
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.929 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.530 0.000 -0.153 -0.090
## 21 Zsdq r2 Zsdq 0.067 NA NA NA NA NA
PE.model3.sdq$est[PE.model3.sdq$op == "r2"]
## [1] 0.06673514
(PE.model2.sdq <- parameterEstimates(model2.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.192 0.033 -5.874 0.000 -0.256 -0.128
## 2 Zsdq ~ SESscore -0.024 0.019 -1.253 0.210 -0.063 0.014
## 3 Zsdq ~ Zgcse -0.216 0.019 -11.322 0.000 -0.253 -0.178
## 4 Zsdq ~~ Zsdq 0.944 0.022 43.329 0.000 0.901 0.987
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.436 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.310 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zsdq ~1 0.118 0.020 5.758 0.000 0.078 0.158
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.930 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zsdq r2 Zsdq 0.059 NA NA NA NA NA
PE.model2.sdq$est[PE.model2.sdq$op == "r2"]
## [1] 0.05875481
(PE.model1.sdq <- parameterEstimates(model1.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.187 0.033 -5.618 0.000 -0.252 -0.121
## 2 Zsdq ~ SESscore -0.126 0.017 -7.214 0.000 -0.160 -0.092
## 3 Zsdq ~~ Zsdq 0.977 0.023 43.317 0.000 0.932 1.021
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.303 0.021 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.383 0.000 0.842 0.903
## 7 Zsdq ~1 0.079 0.021 3.831 0.000 0.038 0.119
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.030 0.012 -2.533 0.011 -0.053 -0.007
## 10 Zsdq r2 Zsdq 0.023 NA NA NA NA NA
PE.model1.sdq$est[PE.model1.sdq$op == "r2"]
## [1] 0.02318273
r2diff2.sdq <- (PE.model2.sdq$est[PE.model2.sdq$op == "r2"] - PE.model1.sdq$est[PE.model1.sdq$op == "r2"])
print(r2diff2.sdq) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.03557208
r2diff3.sdq <- (PE.model3.sdq$est[PE.model3.sdq$op == "r2"] - PE.model2.sdq$est[PE.model2.sdq$op == "r2"])
print(r2diff3.sdq) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.007980322
model1.alc <- 'Zalc ~ sex1 + SESscore'
model1.alcfit <- sem(model1.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 68.423
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -17749.215
## Loglikelihood unrestricted model (H1) -17749.215
##
## Akaike (AIC) 35516.431
## Bayesian (BIC) 35577.430
## Sample-size adjusted Bayesian (SABIC) 35548.830
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.223 0.036 6.124 0.000 0.151 0.294
## SESscore 0.101 0.019 5.275 0.000 0.064 0.139
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.286 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.091 0.022 -4.076 0.000 -0.134 -0.047
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.029 0.012 -2.512 0.012 -0.052 -0.006
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.978 0.025 39.800 0.000 0.930 1.026
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.386 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zalc 0.022
standardizedsolution(model1.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.111 0.018 6.172 0.000 0.076 0.146
## 2 Zalc ~ SESscore 0.095 0.018 5.303 0.000 0.060 0.130
## 3 Zalc ~~ Zalc 0.978 0.005 188.225 0.000 0.968 0.988
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.289 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zalc ~1 -0.091 0.022 -4.092 0.000 -0.134 -0.047
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.031 0.013 -2.511 0.012 -0.056 -0.007
model2.alc <- 'Zalc ~ sex1 + SESscore + Zgcse'
model2.alcfit <- sem(model2.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(model2.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 70.049
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -26116.231
## Loglikelihood unrestricted model (H1) -26116.231
##
## Akaike (AIC) 52260.463
## Bayesian (BIC) 52355.351
## Sample-size adjusted Bayesian (SABIC) 52310.862
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.222 0.036 6.119 0.000 0.151 0.294
## SESscore 0.112 0.022 5.152 0.000 0.069 0.154
## Zgcse -0.020 0.021 -0.923 0.356 -0.061 0.022
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.431 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.442 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.087 0.023 -3.831 0.000 -0.131 -0.042
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.923 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.978 0.025 39.800 0.000 0.930 1.026
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.308 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zalc 0.023
standardizedsolution(model2.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.111 0.018 6.167 0.000 0.076 0.146
## 2 Zalc ~ SESscore 0.105 0.020 5.179 0.000 0.065 0.144
## 3 Zalc ~ Zgcse -0.020 0.021 -0.923 0.356 -0.061 0.022
## 4 Zalc ~~ Zalc 0.977 0.005 184.172 0.000 0.967 0.988
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.030 0.012 2.434 0.015 0.006 0.055
## 7 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 8 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 9 SESscore ~~ Zgcse 0.478 0.010 49.364 0.000 0.459 0.497
## 10 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zalc ~1 -0.087 0.023 -3.844 0.000 -0.131 -0.042
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 SESscore ~1 -0.037 0.013 -2.922 0.003 -0.061 -0.012
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
model3.alc <- 'Zalc ~ sex1 + SESscore + Zgcse + Zhqual'
model3.alcfit <- sem(model3.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(model3.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 20
##
## Number of observations 6488
## Number of missing patterns 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 71.629
## Degrees of freedom 4
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30713.857
## Loglikelihood unrestricted model (H1) -30713.857
##
## Akaike (AIC) 61467.714
## Bayesian (BIC) 61603.269
## Sample-size adjusted Bayesian (SABIC) 61539.714
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.224 0.036 6.158 0.000 0.153 0.295
## SESscore 0.109 0.022 5.007 0.000 0.067 0.152
## Zgcse -0.033 0.024 -1.386 0.166 -0.080 0.014
## Zhqual 0.027 0.022 1.207 0.227 -0.017 0.071
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.597 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.280 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.542 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.085 0.023 -3.736 0.000 -0.129 -0.040
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.922 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.507 0.000 -0.152 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.977 0.025 39.799 0.000 0.929 1.025
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.313 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.578 0.000 0.991 1.087
##
## R-Square:
## Estimate
## Zalc 0.023
standardizedsolution(model3.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.112 0.018 6.208 0.000 0.076 0.147
## 2 Zalc ~ SESscore 0.102 0.020 5.032 0.000 0.062 0.142
## 3 Zalc ~ Zgcse -0.033 0.024 -1.387 0.165 -0.080 0.014
## 4 Zalc ~ Zhqual 0.028 0.023 1.207 0.227 -0.017 0.072
## 5 Zalc ~~ Zalc 0.977 0.005 180.075 0.000 0.966 0.987
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.030 0.012 2.429 0.015 0.006 0.055
## 8 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 9 sex1 ~~ Zhqual -0.041 0.016 -2.605 0.009 -0.071 -0.010
## 10 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 11 SESscore ~~ Zgcse 0.478 0.010 49.348 0.000 0.459 0.497
## 12 SESscore ~~ Zhqual 0.359 0.014 26.385 0.000 0.332 0.385
## 13 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 14 Zgcse ~~ Zhqual 0.554 0.012 47.839 0.000 0.531 0.577
## 15 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 16 Zalc ~1 -0.085 0.023 -3.748 0.000 -0.129 -0.040
## 17 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 18 SESscore ~1 -0.037 0.013 -2.922 0.003 -0.061 -0.012
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.119 0.016 -7.572 0.000 -0.149 -0.088
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.alc <- parameterEstimates(model3.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.224 0.036 6.158 0.000 0.153 0.295
## 2 Zalc ~ SESscore 0.109 0.022 5.007 0.000 0.067 0.152
## 3 Zalc ~ Zgcse -0.033 0.024 -1.386 0.166 -0.080 0.014
## 4 Zalc ~ Zhqual 0.027 0.022 1.207 0.227 -0.017 0.071
## 5 Zalc ~~ Zalc 0.977 0.025 39.799 0.000 0.929 1.025
## 6 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 7 sex1 ~~ SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## 8 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 9 sex1 ~~ Zhqual -0.021 0.008 -2.597 0.009 -0.036 -0.005
## 10 SESscore ~~ SESscore 0.875 0.016 56.313 0.000 0.844 0.905
## 11 SESscore ~~ Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
## 12 SESscore ~~ Zhqual 0.342 0.015 22.280 0.000 0.312 0.372
## 13 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 14 Zgcse ~~ Zhqual 0.565 0.018 31.542 0.000 0.530 0.600
## 15 Zhqual ~~ Zhqual 1.039 0.024 42.578 0.000 0.991 1.087
## 16 Zalc ~1 -0.085 0.023 -3.736 0.000 -0.129 -0.040
## 17 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 18 SESscore ~1 -0.034 0.012 -2.922 0.003 -0.057 -0.011
## 19 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 20 Zhqual ~1 -0.121 0.016 -7.507 0.000 -0.152 -0.089
## 21 Zalc r2 Zalc 0.023 NA NA NA NA NA
PE.model3.alc$est[PE.model3.alc$op == "r2"]
## [1] 0.02338286
(PE.model2.alc <- parameterEstimates(model2.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.222 0.036 6.119 0.000 0.151 0.294
## 2 Zalc ~ SESscore 0.112 0.022 5.152 0.000 0.069 0.154
## 3 Zalc ~ Zgcse -0.020 0.021 -0.923 0.356 -0.061 0.022
## 4 Zalc ~~ Zalc 0.978 0.025 39.800 0.000 0.930 1.026
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ SESscore 0.014 0.006 2.431 0.015 0.003 0.026
## 7 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 8 SESscore ~~ SESscore 0.875 0.016 56.308 0.000 0.844 0.905
## 9 SESscore ~~ Zgcse 0.447 0.013 34.442 0.000 0.422 0.473
## 10 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 11 Zalc ~1 -0.087 0.023 -3.831 0.000 -0.131 -0.042
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 SESscore ~1 -0.034 0.012 -2.923 0.003 -0.057 -0.011
## 14 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 15 Zalc r2 Zalc 0.023 NA NA NA NA NA
PE.model2.alc$est[PE.model2.alc$op == "r2"]
## [1] 0.02263004
(PE.model1.alc <- parameterEstimates(model1.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.223 0.036 6.124 0.000 0.151 0.294
## 2 Zalc ~ SESscore 0.101 0.019 5.275 0.000 0.064 0.139
## 3 Zalc ~~ Zalc 0.978 0.025 39.800 0.000 0.930 1.026
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ SESscore 0.013 0.006 2.286 0.022 0.002 0.025
## 6 SESscore ~~ SESscore 0.873 0.015 56.386 0.000 0.842 0.903
## 7 Zalc ~1 -0.091 0.022 -4.076 0.000 -0.134 -0.047
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 SESscore ~1 -0.029 0.012 -2.512 0.012 -0.052 -0.006
## 10 Zalc r2 Zalc 0.022 NA NA NA NA NA
PE.model1.alc$est[PE.model1.alc$op == "r2"]
## [1] 0.02191005
r2diff2.alc <- (PE.model2.alc$est[PE.model2.alc$op == "r2"] - PE.model1.alc$est[PE.model1.alc$op == "r2"])
print(r2diff2.alc) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.0007199847
r2diff3.alc <- (PE.model3.alc$est[PE.model3.alc$op == "r2"] - PE.model2.alc$est[PE.model2.alc$op == "r2"])
print(r2diff3.alc) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.0007528224
#Logistic and multi-nominal regression for categorical outcomes (w/o moderation)
logistic regression (ordered sub-command) doesn’t work with FIML in sem-function, we use listwise deletion here instead
logistic regression usually uses logit link, but not (yet) implemented in lavaan, instead probit is suggested “You can get approximate logits from probits as Beta_logit=1.7xBeta_probit. Then, OR =exp(Beta_logit).” (according to lavaan forum online)
Logit transforms probabilities into log-odds, whereas probit transforms probabilities into z-scores from a standard normal distribution (e.g., a probability of 50% is associated with a z-score of 0, and probability of 84% is associated with a z-score of 1). Effects can be interpeted as changes in units of SD for the transformed outcome variable.
How many missings are there for benefit status and employment status?
freq_status <- freq(df$status1) #3743 valid cases, 2745 missing
freq_benf <- freq(df$u1cbenf11) #3735 valid cases, 2752 missing
model1.benf <- 'u1cbenf11 ~ sex1 + SESscore'
model1.benffit <- sem(model1.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(model1.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3691 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.173 0.077 -2.239 0.025 -0.325 -0.022
## SESscore -0.244 0.038 -6.359 0.000 -0.319 -0.169
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.644 0.045 36.465 0.000 1.555 1.732
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.057
standardizedsolution(model1.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.082 0.036 -2.254 0.024 -0.153 -0.011
## 2 u1cbenf11 ~ SESscore -0.221 0.033 -6.684 0.000 -0.286 -0.156
## 3 u1cbenf11 | t1 1.596 0.046 34.636 0.000 1.505 1.686
## 4 u1cbenf11 ~~ u1cbenf11 0.943 0.016 59.461 0.000 0.911 0.974
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.050 0.000 NA NA 0.050 0.050
## 7 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 8 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 9 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.788 0.000 NA NA 0.788 0.788
## 11 SESscore ~1 0.060 0.000 NA NA 0.060 0.060
model2.benf <- 'u1cbenf11 ~ sex1 + SESscore + Zgcse'
model2.benffit <- sem(model2.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(model2.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3691 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.180 0.078 -2.299 0.022 -0.333 -0.027
## SESscore -0.136 0.043 -3.165 0.002 -0.220 -0.052
## Zgcse -0.234 0.041 -5.656 0.000 -0.315 -0.153
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.633 0.046 35.662 0.000 1.544 1.723
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.091
standardizedsolution(model2.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.083 0.036 -2.315 0.021 -0.154 -0.013
## 2 u1cbenf11 ~ SESscore -0.121 0.038 -3.207 0.001 -0.195 -0.047
## 3 u1cbenf11 ~ Zgcse -0.210 0.036 -5.862 0.000 -0.281 -0.140
## 4 u1cbenf11 | t1 1.557 0.047 33.393 0.000 1.466 1.649
## 5 u1cbenf11 ~~ u1cbenf11 0.909 0.019 47.316 0.000 0.871 0.947
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.050 0.000 NA NA 0.050 0.050
## 8 sex1 ~~ Zgcse 0.012 0.000 NA NA 0.012 0.012
## 9 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 10 SESscore ~~ Zgcse 0.466 0.000 NA NA 0.466 0.466
## 11 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 12 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 13 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.788 0.000 NA NA 0.788 0.788
## 15 SESscore ~1 0.060 0.000 NA NA 0.060 0.060
## 16 Zgcse ~1 0.212 0.000 NA NA 0.212 0.212
model3.benf <- 'u1cbenf11 ~ sex1 + SESscore + Zgcse + Zhqual'
model3.benffit <- sem(model3.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(model3.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 19 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 3628 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.178 0.080 -2.235 0.025 -0.335 -0.022
## SESscore -0.119 0.044 -2.683 0.007 -0.206 -0.032
## Zgcse -0.107 0.048 -2.224 0.026 -0.201 -0.013
## Zhqual -0.204 0.037 -5.571 0.000 -0.275 -0.132
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.688 0.050 33.832 0.000 1.590 1.785
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.106
standardizedsolution(model3.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.082 0.036 -2.248 0.025 -0.154 -0.011
## 2 u1cbenf11 ~ SESscore -0.105 0.039 -2.712 0.007 -0.180 -0.029
## 3 u1cbenf11 ~ Zgcse -0.094 0.042 -2.244 0.025 -0.176 -0.012
## 4 u1cbenf11 ~ Zhqual -0.192 0.034 -5.685 0.000 -0.259 -0.126
## 5 u1cbenf11 | t1 1.596 0.049 32.887 0.000 1.500 1.691
## 6 u1cbenf11 ~~ u1cbenf11 0.894 0.020 44.880 0.000 0.855 0.933
## 7 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 8 sex1 ~~ SESscore 0.049 0.000 NA NA 0.049 0.049
## 9 sex1 ~~ Zgcse 0.009 0.000 NA NA 0.009 0.009
## 10 sex1 ~~ Zhqual -0.007 0.000 NA NA -0.007 -0.007
## 11 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 12 SESscore ~~ Zgcse 0.458 0.000 NA NA 0.458 0.458
## 13 SESscore ~~ Zhqual 0.340 0.000 NA NA 0.340 0.340
## 14 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 15 Zgcse ~~ Zhqual 0.529 0.000 NA NA 0.529 0.529
## 16 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 17 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 18 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.791 0.000 NA NA 0.791 0.791
## 20 SESscore ~1 0.068 0.000 NA NA 0.068 0.068
## 21 Zgcse ~1 0.230 0.000 NA NA 0.230 0.230
## 22 Zhqual ~1 0.003 0.000 NA NA 0.003 0.003
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.benf <- parameterEstimates(model3.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.178 0.080 -2.235 0.025 -0.335 -0.022
## 2 u1cbenf11 ~ SESscore -0.119 0.044 -2.683 0.007 -0.206 -0.032
## 3 u1cbenf11 ~ Zgcse -0.107 0.048 -2.224 0.026 -0.201 -0.013
## 4 u1cbenf11 ~ Zhqual -0.204 0.037 -5.571 0.000 -0.275 -0.132
## 5 u1cbenf11 | t1 1.688 0.050 33.832 0.000 1.590 1.785
## 6 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 8 sex1 ~~ SESscore 0.022 0.000 NA NA 0.022 0.022
## 9 sex1 ~~ Zgcse 0.004 0.000 NA NA 0.004 0.004
## 10 sex1 ~~ Zhqual -0.004 0.000 NA NA -0.004 -0.004
## 11 SESscore ~~ SESscore 0.865 0.000 NA NA 0.865 0.865
## 12 SESscore ~~ Zgcse 0.397 0.000 NA NA 0.397 0.397
## 13 SESscore ~~ Zhqual 0.316 0.000 NA NA 0.316 0.316
## 14 Zgcse ~~ Zgcse 0.868 0.000 NA NA 0.868 0.868
## 15 Zgcse ~~ Zhqual 0.492 0.000 NA NA 0.492 0.492
## 16 Zhqual ~~ Zhqual 0.998 0.000 NA NA 0.998 0.998
## 17 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 18 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.385 0.000 NA NA 0.385 0.385
## 20 SESscore ~1 0.063 0.000 NA NA 0.063 0.063
## 21 Zgcse ~1 0.215 0.000 NA NA 0.215 0.215
## 22 Zhqual ~1 0.003 0.000 NA NA 0.003 0.003
## 23 u1cbenf11 r2 u1cbenf11 0.106 NA NA NA NA NA
PE.model3.benf$est[PE.model3.benf$op == "r2"]
## [1] 0.1061686
(PE.model2.benf <- parameterEstimates(model2.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.180 0.078 -2.299 0.022 -0.333 -0.027
## 2 u1cbenf11 ~ SESscore -0.136 0.043 -3.165 0.002 -0.220 -0.052
## 3 u1cbenf11 ~ Zgcse -0.234 0.041 -5.656 0.000 -0.315 -0.153
## 4 u1cbenf11 | t1 1.633 0.046 35.662 0.000 1.544 1.723
## 5 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.236 0.000 NA NA 0.236 0.236
## 7 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 8 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 9 SESscore ~~ SESscore 0.871 0.000 NA NA 0.871 0.871
## 10 SESscore ~~ Zgcse 0.410 0.000 NA NA 0.410 0.410
## 11 Zgcse ~~ Zgcse 0.891 0.000 NA NA 0.891 0.891
## 12 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 13 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.383 0.000 NA NA 0.383 0.383
## 15 SESscore ~1 0.056 0.000 NA NA 0.056 0.056
## 16 Zgcse ~1 0.201 0.000 NA NA 0.201 0.201
## 17 u1cbenf11 r2 u1cbenf11 0.091 NA NA NA NA NA
PE.model2.benf$est[PE.model2.benf$op == "r2"]
## [1] 0.09107141
(PE.model1.benf <- parameterEstimates(model1.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.173 0.077 -2.239 0.025 -0.325 -0.022
## 2 u1cbenf11 ~ SESscore -0.244 0.038 -6.359 0.000 -0.319 -0.169
## 3 u1cbenf11 | t1 1.644 0.045 36.465 0.000 1.555 1.732
## 4 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.236 0.000 NA NA 0.236 0.236
## 6 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 7 SESscore ~~ SESscore 0.871 0.000 NA NA 0.871 0.871
## 8 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 9 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.383 0.000 NA NA 0.383 0.383
## 11 SESscore ~1 0.056 0.000 NA NA 0.056 0.056
## 12 u1cbenf11 r2 u1cbenf11 0.057 NA NA NA NA NA
PE.model1.benf$est[PE.model1.benf$op == "r2"]
## [1] 0.05743743
r2diff2.benf <- (PE.model2.benf$est[PE.model2.benf$op == "r2"] - PE.model1.benf$est[PE.model1.benf$op == "r2"])
print(r2diff2.benf) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.03363398
r2diff3.benf <- (PE.model3.benf$est[PE.model3.benf$op == "r2"] - PE.model2.benf$est[PE.model2.benf$op == "r2"])
print(r2diff3.benf) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.01509724
model1.status_bin <- 'status_bin ~ sex1 + SESscore'
model1.status_binfit <- sem(model1.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(model1.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 5 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.012 0.057 -0.203 0.839 -0.124 0.101
## SESscore -0.059 0.029 -2.026 0.043 -0.116 -0.002
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.274 0.036 -35.695 0.000 -1.344 -1.204
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.003
standardizedsolution(model1.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.006 0.028 -0.203 0.839 -0.060 0.049
## 2 status_bin ~ SESscore -0.055 0.027 -2.032 0.042 -0.109 -0.002
## 3 status_bin | t1 -1.272 0.035 -35.924 0.000 -1.342 -1.203
## 4 status_bin ~~ status_bin 0.997 0.003 329.135 0.000 0.991 1.003
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 7 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 8 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 9 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
model2.status_bin <- 'status_bin ~ sex1 + SESscore + Zgcse'
model2.status_binfit <- sem(model2.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(model2.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.011 0.057 -0.200 0.841 -0.124 0.101
## SESscore -0.064 0.034 -1.880 0.060 -0.131 0.003
## Zgcse 0.011 0.033 0.319 0.750 -0.054 0.076
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.272 0.036 -35.294 0.000 -1.343 -1.202
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.003
standardizedsolution(model2.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.006 0.028 -0.200 0.841 -0.060 0.049
## 2 status_bin ~ SESscore -0.060 0.032 -1.885 0.059 -0.122 0.002
## 3 status_bin ~ Zgcse 0.010 0.031 0.319 0.750 -0.051 0.071
## 4 status_bin | t1 -1.270 0.036 -35.453 0.000 -1.340 -1.200
## 5 status_bin ~~ status_bin 0.997 0.003 319.453 0.000 0.991 1.003
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 8 sex1 ~~ Zgcse 0.014 0.000 NA NA 0.014 0.014
## 9 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 10 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 11 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 12 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 13 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 16 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
model3.status_bin <- 'status_bin ~ sex1 + SESscore + Zgcse + Zhqual'
model3.status_binfit <- sem(model3.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(model3.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 12 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.008 0.058 -0.142 0.887 -0.122 0.105
## SESscore -0.069 0.035 -1.984 0.047 -0.138 -0.001
## Zgcse -0.039 0.037 -1.051 0.293 -0.112 0.034
## Zhqual 0.100 0.033 3.030 0.002 0.035 0.165
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.284 0.037 -34.269 0.000 -1.357 -1.210
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.009
standardizedsolution(model3.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.004 0.028 -0.142 0.887 -0.059 0.051
## 2 status_bin ~ SESscore -0.064 0.032 -1.990 0.047 -0.128 -0.001
## 3 status_bin ~ Zgcse -0.036 0.034 -1.051 0.293 -0.104 0.031
## 4 status_bin ~ Zhqual 0.099 0.033 3.051 0.002 0.036 0.163
## 5 status_bin | t1 -1.278 0.037 -34.896 0.000 -1.349 -1.206
## 6 status_bin ~~ status_bin 0.991 0.005 184.027 0.000 0.980 1.001
## 7 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 8 sex1 ~~ SESscore 0.051 0.000 NA NA 0.051 0.051
## 9 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 10 sex1 ~~ Zhqual -0.006 0.000 NA NA -0.006 -0.006
## 11 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 12 SESscore ~~ Zgcse 0.459 0.000 NA NA 0.459 0.459
## 13 SESscore ~~ Zhqual 0.340 0.000 NA NA 0.340 0.340
## 14 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 15 Zgcse ~~ Zhqual 0.528 0.000 NA NA 0.528 0.528
## 16 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 17 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 18 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.792 0.000 NA NA 0.792 0.792
## 20 SESscore ~1 0.066 0.000 NA NA 0.066 0.066
## 21 Zgcse ~1 0.233 0.000 NA NA 0.233 0.233
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.status_bin <- parameterEstimates(model3.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.008 0.058 -0.142 0.887 -0.122 0.105
## 2 status_bin ~ SESscore -0.069 0.035 -1.984 0.047 -0.138 -0.001
## 3 status_bin ~ Zgcse -0.039 0.037 -1.051 0.293 -0.112 0.034
## 4 status_bin ~ Zhqual 0.100 0.033 3.030 0.002 0.035 0.165
## 5 status_bin | t1 -1.284 0.037 -34.269 0.000 -1.357 -1.210
## 6 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 8 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 9 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 10 sex1 ~~ Zhqual -0.003 0.000 NA NA -0.003 -0.003
## 11 SESscore ~~ SESscore 0.868 0.000 NA NA 0.868 0.868
## 12 SESscore ~~ Zgcse 0.398 0.000 NA NA 0.398 0.398
## 13 SESscore ~~ Zhqual 0.316 0.000 NA NA 0.316 0.316
## 14 Zgcse ~~ Zgcse 0.865 0.000 NA NA 0.865 0.865
## 15 Zgcse ~~ Zhqual 0.490 0.000 NA NA 0.490 0.490
## 16 Zhqual ~~ Zhqual 0.997 0.000 NA NA 0.997 0.997
## 17 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 18 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.385 0.000 NA NA 0.385 0.385
## 20 SESscore ~1 0.062 0.000 NA NA 0.062 0.062
## 21 Zgcse ~1 0.217 0.000 NA NA 0.217 0.217
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
## 23 status_bin r2 status_bin 0.009 NA NA NA NA NA
PE.model3.status_bin$est[PE.model3.status_bin$op == "r2"]
## [1] 0.009364356
(PE.model2.status_bin <- parameterEstimates(model2.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.011 0.057 -0.200 0.841 -0.124 0.101
## 2 status_bin ~ SESscore -0.064 0.034 -1.880 0.060 -0.131 0.003
## 3 status_bin ~ Zgcse 0.011 0.033 0.319 0.750 -0.054 0.076
## 4 status_bin | t1 -1.272 0.036 -35.294 0.000 -1.343 -1.202
## 5 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 8 sex1 ~~ Zgcse 0.007 0.000 NA NA 0.007 0.007
## 9 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 10 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 11 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 12 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 13 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 16 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 17 status_bin r2 status_bin 0.003 NA NA NA NA NA
PE.model2.status_bin$est[PE.model2.status_bin$op == "r2"]
## [1] 0.003209703
(PE.model1.status_bin <- parameterEstimates(model1.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.012 0.057 -0.203 0.839 -0.124 0.101
## 2 status_bin ~ SESscore -0.059 0.029 -2.026 0.043 -0.116 -0.002
## 3 status_bin | t1 -1.274 0.036 -35.695 0.000 -1.344 -1.204
## 4 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 7 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 8 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 9 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 12 status_bin r2 status_bin 0.003 NA NA NA NA NA
PE.model1.status_bin$est[PE.model1.status_bin$op == "r2"]
## [1] 0.003117604
r2diff2.status_bin <- (PE.model2.status_bin$est[PE.model2.status_bin$op == "r2"] - PE.model1.status_bin$est[PE.model1.status_bin$op == "r2"])
print(r2diff2.status_bin) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 9.209957e-05
r2diff3.status_bin <- (PE.model3.status_bin$est[PE.model3.status_bin$op == "r2"] - PE.model2.status_bin$est[PE.model2.status_bin$op == "r2"])
print(r2diff3.status_bin) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.006154653
“Multinomial” regression for nominal version of employment status (w/o moderation)
employment status variable is nominal (according to coding specified in prereg): 0=unemployed; 1=working; 2=studying or apprenticeship; 3=full-time parents; 4=gap year/travelling
true multinomial regression is not available in lavaan and the status variable can’t be included in SEM model in the logistic way with the ordered command, because it is neither binary nor are the categories ordered –> needs to be dummy coded into 4 variables before entering into 4 separate logistic regression analyses
#dummy code status variable
#specify status as factor, create 4 dummy variables for originally 5 categories (unemployed is always set as the reference category), and bind new variables to df
df$status1 = as.factor(df$status1)
st_working <- ifelse(df$status1 == '1', 1, 0)
st_studying <- ifelse(df$status1 == '2', 1, 0)
st_parent <- ifelse(df$status1 == '3', 1, 0)
st_gapyear <- ifelse(df$status1 == '4', 1, 0)
df_dummy = cbind(df, st_working, st_studying, st_parent, st_gapyear)
write.csv(df_dummy, '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_random1_dummy.csv', row.names = F, na = 'NA')
##employment status: working vs. unemployed
model1.st_working <- 'st_working ~ sex1 + SESscore'
model1.st_workingfit <- sem(model1.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(model1.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.105 0.043 -2.443 0.015 -0.190 -0.021
## SESscore -0.305 0.023 -13.412 0.000 -0.350 -0.260
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.094 0.027 -3.512 0.000 -0.146 -0.041
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.079
standardizedsolution(model1.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.049 0.020 -2.449 0.014 -0.088 -0.010
## 2 st_working ~ SESscore -0.274 0.019 -14.498 0.000 -0.311 -0.237
## 3 st_working | t1 -0.090 0.025 -3.523 0.000 -0.140 -0.040
## 4 st_working ~~ st_working 0.921 0.011 87.040 0.000 0.901 0.942
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 7 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 8 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 9 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
model2.st_working <- 'st_working ~ sex1 + SESscore + Zgcse'
model2.st_workingfit <- sem(model2.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(model2.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.112 0.043 -2.567 0.010 -0.197 -0.026
## SESscore -0.180 0.025 -7.062 0.000 -0.230 -0.130
## Zgcse -0.277 0.025 -11.290 0.000 -0.326 -0.229
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.148 0.027 -5.407 0.000 -0.201 -0.094
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.124
standardizedsolution(model2.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.051 0.020 -2.573 0.01 -0.089 -0.012
## 2 st_working ~ SESscore -0.157 0.022 -7.204 0.00 -0.200 -0.115
## 3 st_working ~ Zgcse -0.245 0.021 -11.816 0.00 -0.285 -0.204
## 4 st_working | t1 -0.138 0.025 -5.447 0.00 -0.188 -0.088
## 5 st_working ~~ st_working 0.876 0.012 72.464 0.00 0.852 0.899
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 8 sex1 ~~ Zgcse 0.014 0.000 NA NA 0.014 0.014
## 9 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 10 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 11 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 13 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 16 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
model3.st_working <- 'st_working ~ sex1 + SESscore + Zgcse + Zhqual'
model3.st_workingfit <- sem(model3.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(model3.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 12 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.122 0.045 -2.720 0.007 -0.209 -0.034
## SESscore -0.141 0.026 -5.392 0.000 -0.192 -0.090
## Zgcse -0.112 0.029 -3.923 0.000 -0.168 -0.056
## Zhqual -0.361 0.025 -14.477 0.000 -0.410 -0.312
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.123 0.028 -4.413 0.000 -0.178 -0.069
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.198
standardizedsolution(model3.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.053 0.019 -2.726 0.006 -0.091 -0.015
## 2 st_working ~ SESscore -0.117 0.022 -5.457 0.000 -0.160 -0.075
## 3 st_working ~ Zgcse -0.093 0.024 -3.935 0.000 -0.140 -0.047
## 4 st_working ~ Zhqual -0.323 0.021 -15.468 0.000 -0.364 -0.282
## 5 st_working | t1 -0.111 0.025 -4.422 0.000 -0.160 -0.062
## 6 st_working ~~ st_working 0.802 0.013 61.695 0.000 0.776 0.827
## 7 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 8 sex1 ~~ SESscore 0.051 0.000 NA NA 0.051 0.051
## 9 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 10 sex1 ~~ Zhqual -0.006 0.000 NA NA -0.006 -0.006
## 11 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 12 SESscore ~~ Zgcse 0.459 0.000 NA NA 0.459 0.459
## 13 SESscore ~~ Zhqual 0.340 0.000 NA NA 0.340 0.340
## 14 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 15 Zgcse ~~ Zhqual 0.528 0.000 NA NA 0.528 0.528
## 16 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 17 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 18 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.792 0.000 NA NA 0.792 0.792
## 20 SESscore ~1 0.066 0.000 NA NA 0.066 0.066
## 21 Zgcse ~1 0.233 0.000 NA NA 0.233 0.233
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.st_working <- parameterEstimates(model3.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.122 0.045 -2.720 0.007 -0.209 -0.034
## 2 st_working ~ SESscore -0.141 0.026 -5.392 0.000 -0.192 -0.090
## 3 st_working ~ Zgcse -0.112 0.029 -3.923 0.000 -0.168 -0.056
## 4 st_working ~ Zhqual -0.361 0.025 -14.477 0.000 -0.410 -0.312
## 5 st_working | t1 -0.123 0.028 -4.413 0.000 -0.178 -0.069
## 6 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 8 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 9 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 10 sex1 ~~ Zhqual -0.003 0.000 NA NA -0.003 -0.003
## 11 SESscore ~~ SESscore 0.868 0.000 NA NA 0.868 0.868
## 12 SESscore ~~ Zgcse 0.398 0.000 NA NA 0.398 0.398
## 13 SESscore ~~ Zhqual 0.316 0.000 NA NA 0.316 0.316
## 14 Zgcse ~~ Zgcse 0.865 0.000 NA NA 0.865 0.865
## 15 Zgcse ~~ Zhqual 0.490 0.000 NA NA 0.490 0.490
## 16 Zhqual ~~ Zhqual 0.997 0.000 NA NA 0.997 0.997
## 17 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 18 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.385 0.000 NA NA 0.385 0.385
## 20 SESscore ~1 0.062 0.000 NA NA 0.062 0.062
## 21 Zgcse ~1 0.217 0.000 NA NA 0.217 0.217
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
## 23 st_working r2 st_working 0.198 NA NA NA NA NA
PE.model3.st_working$est[PE.model3.st_working$op == "r2"]
## [1] 0.1980484
(PE.model2.st_working <- parameterEstimates(model2.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.112 0.043 -2.567 0.01 -0.197 -0.026
## 2 st_working ~ SESscore -0.180 0.025 -7.062 0.00 -0.230 -0.130
## 3 st_working ~ Zgcse -0.277 0.025 -11.290 0.00 -0.326 -0.229
## 4 st_working | t1 -0.148 0.027 -5.407 0.00 -0.201 -0.094
## 5 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 8 sex1 ~~ Zgcse 0.007 0.000 NA NA 0.007 0.007
## 9 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 10 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 11 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 12 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 13 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 16 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 17 st_working r2 st_working 0.124 NA NA NA NA NA
PE.model2.st_working$est[PE.model2.st_working$op == "r2"]
## [1] 0.1243634
(PE.model1.st_working <- parameterEstimates(model1.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.105 0.043 -2.443 0.015 -0.190 -0.021
## 2 st_working ~ SESscore -0.305 0.023 -13.412 0.000 -0.350 -0.260
## 3 st_working | t1 -0.094 0.027 -3.512 0.000 -0.146 -0.041
## 4 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 7 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 8 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 9 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 12 st_working r2 st_working 0.079 NA NA NA NA NA
PE.model1.st_working$est[PE.model1.st_working$op == "r2"]
## [1] 0.07868862
r2diff2.st_working <- (PE.model2.st_working$est[PE.model2.st_working$op == "r2"] - PE.model1.st_working$est[PE.model1.st_working$op == "r2"])
print(r2diff2.st_working) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.04567473
r2diff3.st_working <- (PE.model3.st_working$est[PE.model3.st_working$op == "r2"] - PE.model2.st_working$est[PE.model2.st_working$op == "r2"])
print(r2diff3.st_working) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.07368505
##employment status: studying/apprenticeship vs. unemployed
model1.st_studying <- 'st_studying ~ sex1 + SESscore'
model1.st_studyingfit <- sem(model1.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(model1.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.103 0.044 2.352 0.019 0.017 0.188
## SESscore 0.290 0.023 12.542 0.000 0.245 0.336
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.365 0.027 13.373 0.000 0.311 0.418
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.072
standardizedsolution(model1.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.048 0.020 2.358 0.018 0.008 0.088
## 2 st_studying ~ SESscore 0.261 0.019 13.462 0.000 0.223 0.299
## 3 st_studying | t1 0.351 0.026 13.544 0.000 0.300 0.402
## 4 st_studying ~~ st_studying 0.928 0.010 89.275 0.000 0.908 0.948
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 7 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 8 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 9 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
model2.st_studying <- 'st_studying ~ sex1 + SESscore + Zgcse'
model2.st_studyingfit <- sem(model2.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(model2.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.111 0.044 2.530 0.011 0.025 0.198
## SESscore 0.156 0.026 6.073 0.000 0.106 0.206
## Zgcse 0.304 0.026 11.866 0.000 0.254 0.354
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.434 0.028 15.255 0.000 0.379 0.490
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.128
standardizedsolution(model2.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.051 0.020 2.537 0.011 0.012 0.090
## 2 st_studying ~ SESscore 0.136 0.022 6.166 0.000 0.093 0.180
## 3 st_studying ~ Zgcse 0.268 0.021 12.577 0.000 0.226 0.309
## 4 st_studying | t1 0.406 0.026 15.704 0.000 0.355 0.456
## 5 st_studying ~~ st_studying 0.872 0.013 68.011 0.000 0.847 0.897
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 8 sex1 ~~ Zgcse 0.014 0.000 NA NA 0.014 0.014
## 9 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 10 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 11 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 13 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 16 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
model3.st_studying <- 'st_studying ~ sex1 + SESscore + Zgcse + Zhqual'
model3.st_studyingfit <- sem(model3.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(model3.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.137 0.046 2.983 0.003 0.047 0.227
## SESscore 0.111 0.027 4.177 0.000 0.059 0.163
## Zgcse 0.101 0.030 3.416 0.001 0.043 0.159
## Zhqual 0.528 0.028 18.883 0.000 0.473 0.582
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.454 0.030 15.102 0.000 0.395 0.513
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.286
standardizedsolution(model3.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.056 0.019 3.000 0.003 0.020 0.093
## 2 st_studying ~ SESscore 0.087 0.021 4.207 0.000 0.047 0.128
## 3 st_studying ~ Zgcse 0.079 0.023 3.421 0.001 0.034 0.125
## 4 st_studying ~ Zhqual 0.445 0.020 21.901 0.000 0.405 0.485
## 5 st_studying | t1 0.384 0.025 15.518 0.000 0.336 0.433
## 6 st_studying ~~ st_studying 0.714 0.015 46.792 0.000 0.684 0.744
## 7 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 8 sex1 ~~ SESscore 0.051 0.000 NA NA 0.051 0.051
## 9 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 10 sex1 ~~ Zhqual -0.006 0.000 NA NA -0.006 -0.006
## 11 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 12 SESscore ~~ Zgcse 0.459 0.000 NA NA 0.459 0.459
## 13 SESscore ~~ Zhqual 0.340 0.000 NA NA 0.340 0.340
## 14 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 15 Zgcse ~~ Zhqual 0.528 0.000 NA NA 0.528 0.528
## 16 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 17 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 18 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.792 0.000 NA NA 0.792 0.792
## 20 SESscore ~1 0.066 0.000 NA NA 0.066 0.066
## 21 Zgcse ~1 0.233 0.000 NA NA 0.233 0.233
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.st_studying <- parameterEstimates(model3.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.137 0.046 2.983 0.003 0.047 0.227
## 2 st_studying ~ SESscore 0.111 0.027 4.177 0.000 0.059 0.163
## 3 st_studying ~ Zgcse 0.101 0.030 3.416 0.001 0.043 0.159
## 4 st_studying ~ Zhqual 0.528 0.028 18.883 0.000 0.473 0.582
## 5 st_studying | t1 0.454 0.030 15.102 0.000 0.395 0.513
## 6 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 8 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 9 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 10 sex1 ~~ Zhqual -0.003 0.000 NA NA -0.003 -0.003
## 11 SESscore ~~ SESscore 0.868 0.000 NA NA 0.868 0.868
## 12 SESscore ~~ Zgcse 0.398 0.000 NA NA 0.398 0.398
## 13 SESscore ~~ Zhqual 0.316 0.000 NA NA 0.316 0.316
## 14 Zgcse ~~ Zgcse 0.865 0.000 NA NA 0.865 0.865
## 15 Zgcse ~~ Zhqual 0.490 0.000 NA NA 0.490 0.490
## 16 Zhqual ~~ Zhqual 0.997 0.000 NA NA 0.997 0.997
## 17 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 18 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.385 0.000 NA NA 0.385 0.385
## 20 SESscore ~1 0.062 0.000 NA NA 0.062 0.062
## 21 Zgcse ~1 0.217 0.000 NA NA 0.217 0.217
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
## 23 st_studying r2 st_studying 0.286 NA NA NA NA NA
PE.model3.st_studying$est[PE.model3.st_studying$op == "r2"]
## [1] 0.2856984
(PE.model2.st_studying <- parameterEstimates(model2.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.111 0.044 2.530 0.011 0.025 0.198
## 2 st_studying ~ SESscore 0.156 0.026 6.073 0.000 0.106 0.206
## 3 st_studying ~ Zgcse 0.304 0.026 11.866 0.000 0.254 0.354
## 4 st_studying | t1 0.434 0.028 15.255 0.000 0.379 0.490
## 5 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 8 sex1 ~~ Zgcse 0.007 0.000 NA NA 0.007 0.007
## 9 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 10 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 11 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 12 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 13 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 16 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 17 st_studying r2 st_studying 0.128 NA NA NA NA NA
PE.model2.st_studying$est[PE.model2.st_studying$op == "r2"]
## [1] 0.1278711
(PE.model1.st_studying <- parameterEstimates(model1.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.103 0.044 2.352 0.019 0.017 0.188
## 2 st_studying ~ SESscore 0.290 0.023 12.542 0.000 0.245 0.336
## 3 st_studying | t1 0.365 0.027 13.373 0.000 0.311 0.418
## 4 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 7 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 8 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 9 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 12 st_studying r2 st_studying 0.072 NA NA NA NA NA
PE.model1.st_studying$est[PE.model1.st_studying$op == "r2"]
## [1] 0.07191247
r2diff2.st_studying <- (PE.model2.st_studying$est[PE.model2.st_studying$op == "r2"] - PE.model1.st_studying$est[PE.model1.st_studying$op == "r2"])
print(r2diff2.st_studying) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.05595861
r2diff3.st_studying <- (PE.model3.st_studying$est[PE.model3.st_studying$op == "r2"] - PE.model2.st_studying$est[PE.model2.st_studying$op == "r2"])
print(r2diff3.st_studying) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.1578273
##employment status: full-time parent vs. unemployed
model1.st_parent <- 'st_parent ~ sex1 + SESscore'
model1.st_parentfit <- sem(model1.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(model1.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.507 0.222 -2.278 0.023 -0.943 -0.071
## SESscore -0.493 0.100 -4.916 0.000 -0.690 -0.296
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.601 0.117 22.308 0.000 2.373 2.830
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.222
standardizedsolution(model1.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.217 0.090 -2.422 0.015 -0.393 -0.041
## 2 st_parent ~ SESscore -0.407 0.068 -5.980 0.000 -0.540 -0.273
## 3 st_parent | t1 2.295 0.111 20.661 0.000 2.077 2.513
## 4 st_parent ~~ st_parent 0.778 0.068 11.375 0.000 0.644 0.912
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 7 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 8 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 9 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
model2.st_parent <- 'st_parent ~ sex1 + SESscore + Zgcse'
model2.st_parentfit <- sem(model2.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(model2.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.542 0.233 -2.332 0.020 -0.998 -0.087
## SESscore -0.352 0.112 -3.155 0.002 -0.571 -0.133
## Zgcse -0.315 0.089 -3.545 0.000 -0.489 -0.141
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.632 0.121 21.673 0.000 2.394 2.870
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.269
standardizedsolution(model2.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.226 0.090 -2.498 0.012 -0.402 -0.049
## 2 st_parent ~ SESscore -0.281 0.082 -3.444 0.001 -0.441 -0.121
## 3 st_parent ~ Zgcse -0.254 0.068 -3.723 0.000 -0.387 -0.120
## 4 st_parent | t1 2.250 0.113 19.944 0.000 2.029 2.471
## 5 st_parent ~~ st_parent 0.731 0.069 10.537 0.000 0.595 0.867
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 8 sex1 ~~ Zgcse 0.014 0.000 NA NA 0.014 0.014
## 9 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 10 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 11 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 13 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 16 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
model3.st_parent <- 'st_parent ~ sex1 + SESscore + Zgcse + Zhqual'
model3.st_parentfit <- sem(model3.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(model3.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.553 0.302 -1.831 0.067 -1.146 0.039
## SESscore -0.312 0.125 -2.494 0.013 -0.556 -0.067
## Zgcse -0.080 0.109 -0.728 0.466 -0.294 0.135
## Zhqual -0.390 0.132 -2.960 0.003 -0.649 -0.132
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.850 0.230 12.403 0.000 2.400 3.300
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.310
standardizedsolution(model3.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.224 0.118 -1.891 0.059 -0.456 0.008
## 2 st_parent ~ SESscore -0.241 0.091 -2.645 0.008 -0.420 -0.062
## 3 st_parent ~ Zgcse -0.062 0.084 -0.737 0.461 -0.225 0.102
## 4 st_parent ~ Zhqual -0.324 0.108 -2.999 0.003 -0.535 -0.112
## 5 st_parent | t1 2.368 0.184 12.858 0.000 2.007 2.729
## 6 st_parent ~~ st_parent 0.690 0.067 10.352 0.000 0.560 0.821
## 7 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 8 sex1 ~~ SESscore 0.051 0.000 NA NA 0.051 0.051
## 9 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 10 sex1 ~~ Zhqual -0.006 0.000 NA NA -0.006 -0.006
## 11 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 12 SESscore ~~ Zgcse 0.459 0.000 NA NA 0.459 0.459
## 13 SESscore ~~ Zhqual 0.340 0.000 NA NA 0.340 0.340
## 14 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 15 Zgcse ~~ Zhqual 0.528 0.000 NA NA 0.528 0.528
## 16 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 17 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 18 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.792 0.000 NA NA 0.792 0.792
## 20 SESscore ~1 0.066 0.000 NA NA 0.066 0.066
## 21 Zgcse ~1 0.233 0.000 NA NA 0.233 0.233
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.st_parent <- parameterEstimates(model3.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.553 0.302 -1.831 0.067 -1.146 0.039
## 2 st_parent ~ SESscore -0.312 0.125 -2.494 0.013 -0.556 -0.067
## 3 st_parent ~ Zgcse -0.080 0.109 -0.728 0.466 -0.294 0.135
## 4 st_parent ~ Zhqual -0.390 0.132 -2.960 0.003 -0.649 -0.132
## 5 st_parent | t1 2.850 0.230 12.403 0.000 2.400 3.300
## 6 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 8 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 9 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 10 sex1 ~~ Zhqual -0.003 0.000 NA NA -0.003 -0.003
## 11 SESscore ~~ SESscore 0.868 0.000 NA NA 0.868 0.868
## 12 SESscore ~~ Zgcse 0.398 0.000 NA NA 0.398 0.398
## 13 SESscore ~~ Zhqual 0.316 0.000 NA NA 0.316 0.316
## 14 Zgcse ~~ Zgcse 0.865 0.000 NA NA 0.865 0.865
## 15 Zgcse ~~ Zhqual 0.490 0.000 NA NA 0.490 0.490
## 16 Zhqual ~~ Zhqual 0.997 0.000 NA NA 0.997 0.997
## 17 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 18 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.385 0.000 NA NA 0.385 0.385
## 20 SESscore ~1 0.062 0.000 NA NA 0.062 0.062
## 21 Zgcse ~1 0.217 0.000 NA NA 0.217 0.217
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
## 23 st_parent r2 st_parent 0.310 NA NA NA NA NA
PE.model3.st_parent$est[PE.model3.st_parent$op == "r2"]
## [1] 0.3096148
(PE.model2.st_parent <- parameterEstimates(model2.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.542 0.233 -2.332 0.020 -0.998 -0.087
## 2 st_parent ~ SESscore -0.352 0.112 -3.155 0.002 -0.571 -0.133
## 3 st_parent ~ Zgcse -0.315 0.089 -3.545 0.000 -0.489 -0.141
## 4 st_parent | t1 2.632 0.121 21.673 0.000 2.394 2.870
## 5 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 8 sex1 ~~ Zgcse 0.007 0.000 NA NA 0.007 0.007
## 9 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 10 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 11 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 12 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 13 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 16 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 17 st_parent r2 st_parent 0.269 NA NA NA NA NA
PE.model2.st_parent$est[PE.model2.st_parent$op == "r2"]
## [1] 0.2692434
(PE.model1.st_parent <- parameterEstimates(model1.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.507 0.222 -2.278 0.023 -0.943 -0.071
## 2 st_parent ~ SESscore -0.493 0.100 -4.916 0.000 -0.690 -0.296
## 3 st_parent | t1 2.601 0.117 22.308 0.000 2.373 2.830
## 4 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 7 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 8 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 9 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 12 st_parent r2 st_parent 0.222 NA NA NA NA NA
PE.model1.st_parent$est[PE.model1.st_parent$op == "r2"]
## [1] 0.2218161
r2diff2.st_parent <- (PE.model2.st_parent$est[PE.model2.st_parent$op == "r2"] - PE.model1.st_parent$est[PE.model1.st_parent$op == "r2"])
print(r2diff2.st_parent) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.04742732
r2diff3.st_parent <- (PE.model3.st_parent$est[PE.model3.st_parent$op == "r2"] - PE.model2.st_parent$est[PE.model2.st_parent$op == "r2"])
print(r2diff3.st_parent) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] 0.04037144
#employment status: gap year/travelling vs. unemployed
model1.st_gapyear <- 'st_gapyear ~ sex1 + SESscore'
model1.st_gapyearfit <- sem(model1.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(model1.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 9 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 -0.103 0.082 -1.250 0.211 -0.264 0.058
## SESscore 0.165 0.043 3.857 0.000 0.081 0.249
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.802 0.050 35.689 0.000 1.703 1.901
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.025
standardizedsolution(model1.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.049 0.039 -1.252 0.211 -0.127 0.028
## 2 st_gapyear ~ SESscore 0.152 0.039 3.947 0.000 0.077 0.228
## 3 st_gapyear | t1 1.780 0.050 35.365 0.000 1.681 1.878
## 4 st_gapyear ~~ st_gapyear 0.975 0.012 81.707 0.000 0.952 0.998
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 7 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 8 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 9 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
model2.st_gapyear <- 'st_gapyear ~ sex1 + SESscore + Zgcse'
model2.st_gapyearfit <- sem(model2.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(model2.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 -0.101 0.083 -1.213 0.225 -0.263 0.062
## SESscore 0.142 0.049 2.892 0.004 0.046 0.238
## Zgcse 0.050 0.051 0.993 0.321 -0.049 0.149
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.814 0.053 34.342 0.000 1.710 1.917
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.027
standardizedsolution(model2.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.048 0.040 -1.215 0.224 -0.126 0.030
## 2 st_gapyear ~ SESscore 0.131 0.045 2.929 0.003 0.043 0.218
## 3 st_gapyear ~ Zgcse 0.047 0.047 0.995 0.320 -0.045 0.139
## 4 st_gapyear | t1 1.789 0.052 34.543 0.000 1.688 1.891
## 5 st_gapyear ~~ st_gapyear 0.973 0.012 79.238 0.000 0.949 0.998
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ SESscore 0.052 0.000 NA NA 0.052 0.052
## 8 sex1 ~~ Zgcse 0.014 0.000 NA NA 0.014 0.014
## 9 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 10 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 11 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 13 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 16 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
model3.st_gapyear <- 'st_gapyear ~ sex1 + SESscore + Zgcse + Zhqual'
model3.st_gapyearfit <- sem(model3.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(model3.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 -0.113 0.083 -1.357 0.175 -0.276 0.050
## SESscore 0.137 0.050 2.741 0.006 0.039 0.235
## Zgcse 0.056 0.056 1.003 0.316 -0.054 0.167
## Zhqual -0.015 0.055 -0.268 0.789 -0.123 0.093
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.805 0.053 33.897 0.000 1.701 1.910
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.025
standardizedsolution(model3.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.054 0.040 -1.359 0.174 -0.133 0.024
## 2 st_gapyear ~ SESscore 0.126 0.045 2.772 0.006 0.037 0.215
## 3 st_gapyear ~ Zgcse 0.052 0.052 1.004 0.315 -0.049 0.153
## 4 st_gapyear ~ Zhqual -0.015 0.054 -0.268 0.789 -0.121 0.092
## 5 st_gapyear | t1 1.783 0.053 33.869 0.000 1.680 1.886
## 6 st_gapyear ~~ st_gapyear 0.975 0.012 82.481 0.000 0.952 0.998
## 7 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 8 sex1 ~~ SESscore 0.051 0.000 NA NA 0.051 0.051
## 9 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 10 sex1 ~~ Zhqual -0.006 0.000 NA NA -0.006 -0.006
## 11 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 12 SESscore ~~ Zgcse 0.459 0.000 NA NA 0.459 0.459
## 13 SESscore ~~ Zhqual 0.340 0.000 NA NA 0.340 0.340
## 14 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 15 Zgcse ~~ Zhqual 0.528 0.000 NA NA 0.528 0.528
## 16 Zhqual ~~ Zhqual 1.000 0.000 NA NA 1.000 1.000
## 17 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 18 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.792 0.000 NA NA 0.792 0.792
## 20 SESscore ~1 0.066 0.000 NA NA 0.066 0.066
## 21 Zgcse ~1 0.233 0.000 NA NA 0.233 0.233
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
#get change in R2 for model1 vs. model2 vs. model3
(PE.model3.st_gapyear <- parameterEstimates(model3.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.113 0.083 -1.357 0.175 -0.276 0.050
## 2 st_gapyear ~ SESscore 0.137 0.050 2.741 0.006 0.039 0.235
## 3 st_gapyear ~ Zgcse 0.056 0.056 1.003 0.316 -0.054 0.167
## 4 st_gapyear ~ Zhqual -0.015 0.055 -0.268 0.789 -0.123 0.093
## 5 st_gapyear | t1 1.805 0.053 33.897 0.000 1.701 1.910
## 6 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 8 sex1 ~~ SESscore 0.023 0.000 NA NA 0.023 0.023
## 9 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 10 sex1 ~~ Zhqual -0.003 0.000 NA NA -0.003 -0.003
## 11 SESscore ~~ SESscore 0.868 0.000 NA NA 0.868 0.868
## 12 SESscore ~~ Zgcse 0.398 0.000 NA NA 0.398 0.398
## 13 SESscore ~~ Zhqual 0.316 0.000 NA NA 0.316 0.316
## 14 Zgcse ~~ Zgcse 0.865 0.000 NA NA 0.865 0.865
## 15 Zgcse ~~ Zhqual 0.490 0.000 NA NA 0.490 0.490
## 16 Zhqual ~~ Zhqual 0.997 0.000 NA NA 0.997 0.997
## 17 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 18 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 19 sex1 ~1 0.385 0.000 NA NA 0.385 0.385
## 20 SESscore ~1 0.062 0.000 NA NA 0.062 0.062
## 21 Zgcse ~1 0.217 0.000 NA NA 0.217 0.217
## 22 Zhqual ~1 0.005 0.000 NA NA 0.005 0.005
## 23 st_gapyear r2 st_gapyear 0.025 NA NA NA NA NA
PE.model3.st_gapyear$est[PE.model3.st_gapyear$op == "r2"]
## [1] 0.02491703
(PE.model2.st_gapyear <- parameterEstimates(model2.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.101 0.083 -1.213 0.225 -0.263 0.062
## 2 st_gapyear ~ SESscore 0.142 0.049 2.892 0.004 0.046 0.238
## 3 st_gapyear ~ Zgcse 0.050 0.051 0.993 0.321 -0.049 0.149
## 4 st_gapyear | t1 1.814 0.053 34.342 0.000 1.710 1.917
## 5 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 8 sex1 ~~ Zgcse 0.007 0.000 NA NA 0.007 0.007
## 9 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 10 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 11 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 12 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 13 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 16 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 17 st_gapyear r2 st_gapyear 0.027 NA NA NA NA NA
PE.model2.st_gapyear$est[PE.model2.st_gapyear$op == "r2"]
## [1] 0.02655772
(PE.model1.st_gapyear <- parameterEstimates(model1.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.103 0.082 -1.250 0.211 -0.264 0.058
## 2 st_gapyear ~ SESscore 0.165 0.043 3.857 0.000 0.081 0.249
## 3 st_gapyear | t1 1.802 0.050 35.689 0.000 1.703 1.901
## 4 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ SESscore 0.024 0.000 NA NA 0.024 0.024
## 7 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 8 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 9 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 12 st_gapyear r2 st_gapyear 0.025 NA NA NA NA NA
PE.model1.st_gapyear$est[PE.model1.st_gapyear$op == "r2"]
## [1] 0.02490141
r2diff2.st_gapyear <- (PE.model2.st_gapyear$est[PE.model2.st_gapyear$op == "r2"] - PE.model1.st_gapyear$est[PE.model1.st_gapyear$op == "r2"])
print(r2diff2.st_gapyear) #difference model1 vs 2, incremental explained variance by GCSE
## [1] 0.001656313
r2diff3.st_gapyear <- (PE.model3.st_gapyear$est[PE.model3.st_gapyear$op == "r2"] - PE.model2.st_gapyear$est[PE.model2.st_gapyear$op == "r2"])
print(r2diff3.st_gapyear) #difference model2 vs 3, incremental explained variance by highest qualification
## [1] -0.001640693
#Step 4: #Regression models with moderation for sex and SES
again series of linear/logistic/multi-nominal regressions for all DVs now with moderation by SES or sex (separately)
Model a1: DV ~ sex1 + Zgcse Model a2: DV ~ sex1 + Zgcse + sex*Zgcse
Model b1: DV ~ SESscore + Zgcse Model b2: DV ~ SESscore + Zgcse + SES*Zgcse
df$sex.gcse <- df$sex1*df$Zgcse
df$SES.gcse <- df$SESscore*df$Zgcse
modela1.hqual <- 'Zhqual ~ sex1 + Zgcse'
modela1.hqualfit <- sem(modela1.hqual, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.hqualfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 12 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1209.253
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18526.245
## Loglikelihood unrestricted model (H1) -18526.245
##
## Akaike (AIC) 37070.489
## Bayesian (BIC) 37131.489
## Sample-size adjusted Bayesian (SABIC) 37102.889
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 -0.026 0.029 -0.899 0.369 -0.082 0.030
## Zgcse 0.565 0.015 37.825 0.000 0.536 0.595
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.108 0.018 -5.973 0.000 -0.143 -0.073
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.720 0.017 42.948 0.000 0.687 0.753
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.308
standardizedsolution(modela1.hqualfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.013 0.014 -0.900 0.368 -0.040 0.015
## 2 Zhqual ~ Zgcse 0.554 0.012 47.820 0.000 0.531 0.577
## 3 Zhqual ~~ Zhqual 0.692 0.013 53.719 0.000 0.667 0.717
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zhqual ~1 -0.106 0.018 -5.993 0.000 -0.140 -0.071
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.hqual <- 'Zhqual ~ sex1 + Zgcse + sex.gcse'
modela2.hqualfit <- sem(modela2.hqual, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.hqualfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1213.586
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23222.754
## Loglikelihood unrestricted model (H1) -23222.754
##
## Akaike (AIC) 46473.508
## Bayesian (BIC) 46568.396
## Sample-size adjusted Bayesian (SABIC) 46523.908
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 -0.039 0.029 -1.336 0.182 -0.097 0.018
## Zgcse 0.540 0.019 27.951 0.000 0.502 0.578
## sex.gcse 0.063 0.030 2.082 0.037 0.004 0.123
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.174 0.002 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.103 0.018 -5.640 0.000 -0.139 -0.067
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.719 0.017 42.948 0.000 0.687 0.752
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.957 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zhqual 0.314
standardizedsolution(modela2.hqualfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.019 0.014 -1.338 0.181 -0.047 0.009
## 2 Zhqual ~ Zgcse 0.527 0.017 30.199 0.000 0.493 0.561
## 3 Zhqual ~ sex.gcse 0.043 0.021 2.090 0.037 0.003 0.084
## 4 Zhqual ~~ Zhqual 0.686 0.013 52.010 0.000 0.661 0.712
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.584 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zhqual ~1 -0.100 0.018 -5.648 0.000 -0.135 -0.066
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.hqual <- 'Zhqual ~ SESscore + Zgcse'
modelb1.hqualfit <- sem(modelb1.hqual, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.hqualfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 9 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1269.436
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -21575.873
## Loglikelihood unrestricted model (H1) -21575.873
##
## Akaike (AIC) 43169.745
## Bayesian (BIC) 43230.745
## Sample-size adjusted Bayesian (SABIC) 43202.145
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## SESscore 0.132 0.017 7.845 0.000 0.099 0.165
## Zgcse 0.505 0.017 30.193 0.000 0.472 0.537
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.421 0.000 0.422 0.472
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.113 0.014 -7.957 0.000 -0.141 -0.085
## SESscore -0.034 0.012 -2.914 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.708 0.017 42.936 0.000 0.676 0.741
## SESscore 0.874 0.016 56.326 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.318
standardizedsolution(modelb1.hqualfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zhqual ~ SESscore 0.122 0.015 7.880 0.000 0.091 0.152
## 2 Zhqual ~ Zgcse 0.495 0.014 34.663 0.000 0.467 0.523
## 3 Zhqual ~~ Zhqual 0.682 0.013 53.266 0.000 0.657 0.708
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.293 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zhqual ~1 -0.111 0.014 -8.030 0.000 -0.138 -0.084
## 8 SESscore ~1 -0.036 0.013 -2.914 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.hqual <- 'Zhqual ~ SESscore + Zgcse + SES.gcse'
modelb2.hqualfit <- sem(modelb2.hqual, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.hqualfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1360.864
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30248.349
## Loglikelihood unrestricted model (H1) -30248.349
##
## Akaike (AIC) 60524.699
## Bayesian (BIC) 60619.587
## Sample-size adjusted Bayesian (SABIC) 60575.098
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## SESscore 0.164 0.017 9.654 0.000 0.131 0.197
## Zgcse 0.501 0.017 30.341 0.000 0.469 0.533
## SES.gcse -0.153 0.016 -9.628 0.000 -0.184 -0.122
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.418 0.000 0.422 0.472
## SES.gcse -0.013 0.011 -1.111 0.267 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.648 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.051 0.015 -3.329 0.001 -0.082 -0.021
## SESscore -0.034 0.012 -2.913 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.804 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.691 0.016 42.913 0.000 0.659 0.722
## SESscore 0.874 0.016 56.329 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.380 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zhqual 0.360
standardizedsolution(modelb2.hqualfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zhqual ~ SESscore 0.148 0.015 9.771 0.000 0.118 0.177
## 2 Zhqual ~ Zgcse 0.482 0.014 34.458 0.000 0.455 0.510
## 3 Zhqual ~ SES.gcse -0.142 0.014 -9.898 0.000 -0.170 -0.114
## 4 Zhqual ~~ Zhqual 0.640 0.013 47.733 0.000 0.614 0.667
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.285 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.111 0.266 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.122 0.012 -9.864 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zhqual ~1 -0.049 0.015 -3.326 0.001 -0.079 -0.020
## 12 SESscore ~1 -0.036 0.013 -2.912 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.005 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.hqual <- parameterEstimates(modela1.hqualfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.026 0.029 -0.899 0.369 -0.082 0.030
## 2 Zhqual ~ Zgcse 0.565 0.015 37.825 0.000 0.536 0.595
## 3 Zhqual ~~ Zhqual 0.720 0.017 42.948 0.000 0.687 0.753
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zhqual ~1 -0.108 0.018 -5.973 0.000 -0.143 -0.073
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zhqual r2 Zhqual 0.308 NA NA NA NA NA
PE.modela1.hqual$est[PE.modela1.hqual$op == "r2"]
## [1] 0.30791
(PE.modela2.hqual <- parameterEstimates(modela2.hqualfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zhqual ~ sex1 -0.039 0.029 -1.336 0.182 -0.097 0.018
## 2 Zhqual ~ Zgcse 0.540 0.019 27.951 0.000 0.502 0.578
## 3 Zhqual ~ sex.gcse 0.063 0.030 2.082 0.037 0.004 0.123
## 4 Zhqual ~~ Zhqual 0.719 0.017 42.948 0.000 0.687 0.752
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.174 0.002 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.957 0.000 0.475 0.509
## 11 Zhqual ~1 -0.103 0.018 -5.640 0.000 -0.139 -0.067
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zhqual r2 Zhqual 0.314 NA NA NA NA NA
PE.modela2.hqual$est[PE.modela2.hqual$op == "r2"]
## [1] 0.3135517
(PE.modelb1.hqual <- parameterEstimates(modelb1.hqualfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zhqual ~ SESscore 0.132 0.017 7.845 0.000 0.099 0.165
## 2 Zhqual ~ Zgcse 0.505 0.017 30.193 0.000 0.472 0.537
## 3 Zhqual ~~ Zhqual 0.708 0.017 42.936 0.000 0.676 0.741
## 4 SESscore ~~ SESscore 0.874 0.016 56.326 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.421 0.000 0.422 0.472
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zhqual ~1 -0.113 0.014 -7.957 0.000 -0.141 -0.085
## 8 SESscore ~1 -0.034 0.012 -2.914 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zhqual r2 Zhqual 0.318 NA NA NA NA NA
PE.modelb1.hqual$est[PE.modelb1.hqual$op == "r2"]
## [1] 0.3175504
(PE.modelb2.hqual <- parameterEstimates(modelb2.hqualfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zhqual ~ SESscore 0.164 0.017 9.654 0.000 0.131 0.197
## 2 Zhqual ~ Zgcse 0.501 0.017 30.341 0.000 0.469 0.533
## 3 Zhqual ~ SES.gcse -0.153 0.016 -9.628 0.000 -0.184 -0.122
## 4 Zhqual ~~ Zhqual 0.691 0.016 42.913 0.000 0.659 0.722
## 5 SESscore ~~ SESscore 0.874 0.016 56.329 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.418 0.000 0.422 0.472
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.111 0.267 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.648 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.380 0.000 0.893 0.957
## 11 Zhqual ~1 -0.051 0.015 -3.329 0.001 -0.082 -0.021
## 12 SESscore ~1 -0.034 0.012 -2.913 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.804 0.000 0.420 0.467
## 15 Zhqual r2 Zhqual 0.360 NA NA NA NA NA
PE.modelb2.hqual$est[PE.modelb2.hqual$op == "r2"]
## [1] 0.3596876
r2diffa.hqual <- (PE.modela2.hqual$est[PE.modela2.hqual$op == "r2"] - PE.modela1.hqual$est[PE.modela1.hqual$op == "r2"])
print(r2diffa.hqual) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.00564173
r2diffb.hqual <- (PE.modelb2.hqual$est[PE.modelb2.hqual$op == "r2"] - PE.modelb1.hqual$est[PE.modelb1.hqual$op == "r2"])
print(r2diffb.hqual) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.04213726
modela1.degree <- 'Zdegree ~ sex1 + Zgcse'
modela1.degreefit <- sem(modela1.degree, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.degreefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 151.823
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -16339.111
## Loglikelihood unrestricted model (H1) -16339.111
##
## Akaike (AIC) 32696.222
## Bayesian (BIC) 32757.221
## Sample-size adjusted Bayesian (SABIC) 32728.621
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 -0.079 0.048 -1.652 0.099 -0.172 0.015
## Zgcse 0.381 0.030 12.562 0.000 0.322 0.441
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.170 0.032 -5.325 0.000 -0.233 -0.107
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.917 0.031 29.791 0.000 0.857 0.978
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.139
standardizedsolution(modela1.degreefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.038 0.023 -1.656 0.098 -0.083 0.007
## 2 Zdegree ~ Zgcse 0.369 0.026 14.177 0.000 0.318 0.420
## 3 Zdegree ~~ Zdegree 0.861 0.020 43.924 0.000 0.822 0.899
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zdegree ~1 -0.165 0.030 -5.426 0.000 -0.224 -0.105
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.degree <- 'Zdegree ~ sex1 + Zgcse + sex.gcse'
modela2.degreefit <- sem(modela2.degree, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.degreefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 156.027
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -21035.685
## Loglikelihood unrestricted model (H1) -21035.685
##
## Akaike (AIC) 42099.370
## Bayesian (BIC) 42194.258
## Sample-size adjusted Bayesian (SABIC) 42149.770
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 -0.006 0.059 -0.107 0.915 -0.122 0.109
## Zgcse 0.426 0.037 11.392 0.000 0.353 0.500
## sex.gcse -0.131 0.064 -2.052 0.040 -0.256 -0.006
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.174 0.002 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.290 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.192 0.034 -5.708 0.000 -0.258 -0.126
## sex1 0.474 0.006 76.502 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.017 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.915 0.031 29.792 0.000 0.855 0.976
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.957 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.957 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zdegree 0.129
standardizedsolution(modela2.degreefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.003 0.029 -0.107 0.915 -0.059 0.053
## 2 Zdegree ~ Zgcse 0.416 0.034 12.152 0.000 0.349 0.483
## 3 Zdegree ~ sex.gcse -0.090 0.044 -2.044 0.041 -0.176 -0.004
## 4 Zdegree ~~ Zdegree 0.871 0.019 45.920 0.000 0.834 0.908
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.585 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zdegree ~1 -0.187 0.032 -5.804 0.000 -0.250 -0.124
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.016 0.003 -0.062 -0.013
modelb1.degree <- 'Zdegree ~ SESscore + Zgcse'
modelb1.degreefit <- sem(modelb1.degree, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.degreefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 149.284
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19420.100
## Loglikelihood unrestricted model (H1) -19420.100
##
## Akaike (AIC) 38858.201
## Bayesian (BIC) 38919.200
## Sample-size adjusted Bayesian (SABIC) 38890.600
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## SESscore 0.012 0.028 0.431 0.666 -0.043 0.068
## Zgcse 0.372 0.033 11.297 0.000 0.308 0.437
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.425 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.196 0.028 -7.094 0.000 -0.251 -0.142
## SESscore -0.034 0.012 -2.915 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.919 0.031 29.792 0.000 0.858 0.979
## SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.135
standardizedsolution(modelb1.degreefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zdegree ~ SESscore 0.011 0.026 0.431 0.666 -0.039 0.062
## 2 Zdegree ~ Zgcse 0.361 0.029 12.428 0.000 0.304 0.418
## 3 Zdegree ~~ Zdegree 0.865 0.019 45.123 0.000 0.828 0.903
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.311 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zdegree ~1 -0.191 0.026 -7.358 0.000 -0.241 -0.140
## 8 SESscore ~1 -0.036 0.013 -2.914 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.degree <- 'Zdegree ~ SESscore + Zgcse + SES.gcse'
modelb2.degreefit <- sem(modelb2.degree, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.degreefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 152.430
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -28136.718
## Loglikelihood unrestricted model (H1) -28136.718
##
## Akaike (AIC) 56301.435
## Bayesian (BIC) 56396.323
## Sample-size adjusted Bayesian (SABIC) 56351.835
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## SESscore 0.041 0.033 1.248 0.212 -0.023 0.105
## Zgcse 0.385 0.034 11.428 0.000 0.319 0.451
## SES.gcse -0.061 0.034 -1.776 0.076 -0.128 0.006
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.120 0.263 -0.035 0.009
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.669 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.186 0.028 -6.599 0.000 -0.242 -0.131
## SESscore -0.034 0.012 -2.913 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.001 0.999 -0.024 0.024
## SES.gcse 0.444 0.012 36.803 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.917 0.031 29.792 0.000 0.857 0.977
## SESscore 0.874 0.016 56.319 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.378 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zdegree 0.158
standardizedsolution(modelb2.degreefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zdegree ~ SESscore 0.036 0.029 1.255 0.209 -0.020 0.093
## 2 Zdegree ~ Zgcse 0.369 0.029 12.864 0.000 0.312 0.425
## 3 Zdegree ~ SES.gcse -0.056 0.031 -1.803 0.071 -0.117 0.005
## 4 Zdegree ~~ Zdegree 0.842 0.025 33.842 0.000 0.793 0.890
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.314 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.120 0.263 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.887 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zdegree ~1 -0.178 0.026 -6.743 0.000 -0.230 -0.127
## 12 SESscore ~1 -0.036 0.013 -2.913 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 -0.001 0.999 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.005 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.degree <- parameterEstimates(modela1.degreefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.079 0.048 -1.652 0.099 -0.172 0.015
## 2 Zdegree ~ Zgcse 0.381 0.030 12.562 0.000 0.322 0.441
## 3 Zdegree ~~ Zdegree 0.917 0.031 29.791 0.000 0.857 0.978
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zdegree ~1 -0.170 0.032 -5.325 0.000 -0.233 -0.107
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zdegree r2 Zdegree 0.139 NA NA NA NA NA
PE.modela1.degree$est[PE.modela1.degree$op == "r2"]
## [1] 0.139219
(PE.modela2.degree <- parameterEstimates(modela2.degreefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zdegree ~ sex1 -0.006 0.059 -0.107 0.915 -0.122 0.109
## 2 Zdegree ~ Zgcse 0.426 0.037 11.392 0.000 0.353 0.500
## 3 Zdegree ~ sex.gcse -0.131 0.064 -2.052 0.040 -0.256 -0.006
## 4 Zdegree ~~ Zdegree 0.915 0.031 29.792 0.000 0.855 0.976
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.174 0.002 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.957 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.290 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.957 0.000 0.475 0.509
## 11 Zdegree ~1 -0.192 0.034 -5.708 0.000 -0.258 -0.126
## 12 sex1 ~1 0.474 0.006 76.502 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.017 0.003 -0.043 -0.009
## 15 Zdegree r2 Zdegree 0.129 NA NA NA NA NA
PE.modela2.degree$est[PE.modela2.degree$op == "r2"]
## [1] 0.1287065
(PE.modelb1.degree <- parameterEstimates(modelb1.degreefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zdegree ~ SESscore 0.012 0.028 0.431 0.666 -0.043 0.068
## 2 Zdegree ~ Zgcse 0.372 0.033 11.297 0.000 0.308 0.437
## 3 Zdegree ~~ Zdegree 0.919 0.031 29.792 0.000 0.858 0.979
## 4 SESscore ~~ SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.425 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zdegree ~1 -0.196 0.028 -7.094 0.000 -0.251 -0.142
## 8 SESscore ~1 -0.034 0.012 -2.915 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zdegree r2 Zdegree 0.135 NA NA NA NA NA
PE.modelb1.degree$est[PE.modelb1.degree$op == "r2"]
## [1] 0.1345458
(PE.modelb2.degree <- parameterEstimates(modelb2.degreefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zdegree ~ SESscore 0.041 0.033 1.248 0.212 -0.023 0.105
## 2 Zdegree ~ Zgcse 0.385 0.034 11.428 0.000 0.319 0.451
## 3 Zdegree ~ SES.gcse -0.061 0.034 -1.776 0.076 -0.128 0.006
## 4 Zdegree ~~ Zdegree 0.917 0.031 29.792 0.000 0.857 0.977
## 5 SESscore ~~ SESscore 0.874 0.016 56.319 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.120 0.263 -0.035 0.009
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.669 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.378 0.000 0.893 0.957
## 11 Zdegree ~1 -0.186 0.028 -6.599 0.000 -0.242 -0.131
## 12 SESscore ~1 -0.034 0.012 -2.913 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 -0.001 0.999 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.803 0.000 0.420 0.467
## 15 Zdegree r2 Zdegree 0.158 NA NA NA NA NA
PE.modelb2.degree$est[PE.modelb2.degree$op == "r2"]
## [1] 0.1582521
r2diffa.degree <- (PE.modela2.degree$est[PE.modela2.degree$op == "r2"] - PE.modela1.degree$est[PE.modela1.degree$op == "r2"])
print(r2diffa.degree) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] -0.0105125
r2diffb.degree <- (PE.modelb2.degree$est[PE.modelb2.degree$op == "r2"] - PE.modelb1.degree$est[PE.modelb1.degree$op == "r2"])
print(r2diffb.degree) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.02370632
modela1.ocprestige <- 'Zsoc ~ sex1 + Zgcse'
modela1.ocprestigefit <- sem(modela1.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 159.936
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -16208.769
## Loglikelihood unrestricted model (H1) -16208.769
##
## Akaike (AIC) 32435.538
## Bayesian (BIC) 32496.538
## Sample-size adjusted Bayesian (SABIC) 32467.938
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.168 0.048 3.469 0.001 0.073 0.262
## Zgcse 0.316 0.025 12.485 0.000 0.267 0.366
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc -0.054 0.029 -1.845 0.065 -0.111 0.003
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.909 0.031 29.034 0.000 0.848 0.970
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zsoc 0.103
standardizedsolution(modela1.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.083 0.024 3.480 0.001 0.036 0.130
## 2 Zsoc ~ Zgcse 0.314 0.023 13.447 0.000 0.269 0.360
## 3 Zsoc ~~ Zsoc 0.897 0.015 60.870 0.000 0.868 0.926
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zsoc ~1 -0.053 0.029 -1.847 0.065 -0.110 0.003
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.ocprestige <- 'Zsoc ~ sex1 + Zgcse + sex.gcse'
modela2.ocprestigefit <- sem(modela2.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 162.480
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -20906.173
## Loglikelihood unrestricted model (H1) -20906.173
##
## Akaike (AIC) 41840.346
## Bayesian (BIC) 41935.234
## Sample-size adjusted Bayesian (SABIC) 41890.746
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.170 0.048 3.509 0.000 0.075 0.264
## Zgcse 0.283 0.033 8.628 0.000 0.219 0.347
## sex.gcse 0.082 0.052 1.596 0.110 -0.019 0.184
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.174 0.002 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc -0.054 0.029 -1.870 0.061 -0.111 0.003
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.908 0.031 29.034 0.000 0.846 0.969
## sex1 0.249 0.004 56.957 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zsoc 0.109
standardizedsolution(modela2.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.084 0.024 3.521 0.000 0.037 0.131
## 2 Zsoc ~ Zgcse 0.281 0.032 8.856 0.000 0.218 0.343
## 3 Zsoc ~ sex.gcse 0.057 0.036 1.602 0.109 -0.013 0.127
## 4 Zsoc ~~ Zsoc 0.891 0.016 57.242 0.000 0.861 0.922
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.585 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zsoc ~1 -0.054 0.029 -1.872 0.061 -0.110 0.003
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.ocprestige <- 'Zsoc ~ SESscore + Zgcse'
modelb1.ocprestigefit <- sem(modelb1.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 154.298
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19291.308
## Loglikelihood unrestricted model (H1) -19291.308
##
## Akaike (AIC) 38600.615
## Bayesian (BIC) 38661.615
## Sample-size adjusted Bayesian (SABIC) 38633.015
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## SESscore 0.073 0.029 2.523 0.012 0.016 0.130
## Zgcse 0.285 0.028 10.059 0.000 0.229 0.340
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.018 0.024 0.749 0.454 -0.029 0.064
## SESscore -0.034 0.012 -2.918 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.912 0.031 29.033 0.000 0.850 0.974
## SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zsoc 0.103
standardizedsolution(modelb1.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ SESscore 0.068 0.027 2.529 0.011 0.015 0.120
## 2 Zsoc ~ Zgcse 0.282 0.027 10.559 0.000 0.230 0.335
## 3 Zsoc ~~ Zsoc 0.897 0.015 60.119 0.000 0.868 0.927
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.313 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zsoc ~1 0.018 0.023 0.749 0.454 -0.028 0.064
## 8 SESscore ~1 -0.037 0.013 -2.917 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.ocprestige <- 'Zsoc ~ SESscore + Zgcse + SES.gcse'
modelb2.ocprestigefit <- sem(modelb2.ocprestige, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.ocprestigefit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 160.578
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -28006.358
## Loglikelihood unrestricted model (H1) -28006.358
##
## Akaike (AIC) 56040.717
## Bayesian (BIC) 56135.605
## Sample-size adjusted Bayesian (SABIC) 56091.116
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## SESscore 0.077 0.029 2.674 0.007 0.021 0.134
## Zgcse 0.273 0.029 9.511 0.000 0.216 0.329
## SES.gcse -0.068 0.027 -2.508 0.012 -0.122 -0.015
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.118 0.263 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.666 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.043 0.026 1.677 0.094 -0.007 0.093
## SESscore -0.034 0.012 -2.918 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.807 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.909 0.031 29.032 0.000 0.847 0.970
## SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zsoc 0.106
standardizedsolution(modelb2.ocprestigefit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsoc ~ SESscore 0.072 0.027 2.682 0.007 0.019 0.124
## 2 Zsoc ~ Zgcse 0.271 0.027 9.927 0.000 0.217 0.324
## 3 Zsoc ~ SES.gcse -0.065 0.026 -2.514 0.012 -0.116 -0.014
## 4 Zsoc ~~ Zsoc 0.894 0.015 59.594 0.000 0.865 0.924
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.313 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.119 0.263 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.884 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zsoc ~1 0.043 0.025 1.679 0.093 -0.007 0.093
## 12 SESscore ~1 -0.037 0.013 -2.917 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.462 0.013 35.009 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.ocprestige <- parameterEstimates(modela1.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.168 0.048 3.469 0.001 0.073 0.262
## 2 Zsoc ~ Zgcse 0.316 0.025 12.485 0.000 0.267 0.366
## 3 Zsoc ~~ Zsoc 0.909 0.031 29.034 0.000 0.848 0.970
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zsoc ~1 -0.054 0.029 -1.845 0.065 -0.111 0.003
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zsoc r2 Zsoc 0.103 NA NA NA NA NA
PE.modela1.ocprestige$est[PE.modela1.ocprestige$op == "r2"]
## [1] 0.102987
(PE.modela2.ocprestige <- parameterEstimates(modela2.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ sex1 0.170 0.048 3.509 0.000 0.075 0.264
## 2 Zsoc ~ Zgcse 0.283 0.033 8.628 0.000 0.219 0.347
## 3 Zsoc ~ sex.gcse 0.082 0.052 1.596 0.110 -0.019 0.184
## 4 Zsoc ~~ Zsoc 0.908 0.031 29.034 0.000 0.846 0.969
## 5 sex1 ~~ sex1 0.249 0.004 56.957 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.174 0.002 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zsoc ~1 -0.054 0.029 -1.870 0.061 -0.111 0.003
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zsoc r2 Zsoc 0.109 NA NA NA NA NA
PE.modela2.ocprestige$est[PE.modela2.ocprestige$op == "r2"]
## [1] 0.1087385
(PE.modelb1.ocprestige <- parameterEstimates(modelb1.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ SESscore 0.073 0.029 2.523 0.012 0.016 0.130
## 2 Zsoc ~ Zgcse 0.285 0.028 10.059 0.000 0.229 0.340
## 3 Zsoc ~~ Zsoc 0.912 0.031 29.033 0.000 0.850 0.974
## 4 SESscore ~~ SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zsoc ~1 0.018 0.024 0.749 0.454 -0.029 0.064
## 8 SESscore ~1 -0.034 0.012 -2.918 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zsoc r2 Zsoc 0.103 NA NA NA NA NA
PE.modelb1.ocprestige$est[PE.modelb1.ocprestige$op == "r2"]
## [1] 0.1026571
(PE.modelb2.ocprestige <- parameterEstimates(modelb2.ocprestigefit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsoc ~ SESscore 0.077 0.029 2.674 0.007 0.021 0.134
## 2 Zsoc ~ Zgcse 0.273 0.029 9.511 0.000 0.216 0.329
## 3 Zsoc ~ SES.gcse -0.068 0.027 -2.508 0.012 -0.122 -0.015
## 4 Zsoc ~~ Zsoc 0.909 0.031 29.032 0.000 0.847 0.970
## 5 SESscore ~~ SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.118 0.263 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.666 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
## 11 Zsoc ~1 0.043 0.026 1.677 0.094 -0.007 0.093
## 12 SESscore ~1 -0.034 0.012 -2.918 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.807 0.000 0.420 0.467
## 15 Zsoc r2 Zsoc 0.106 NA NA NA NA NA
PE.modelb2.ocprestige$est[PE.modelb2.ocprestige$op == "r2"]
## [1] 0.1055931
r2diffa.ocprestige <- (PE.modela2.ocprestige$est[PE.modela2.ocprestige$op == "r2"] - PE.modela1.ocprestige$est[PE.modela1.ocprestige$op == "r2"])
print(r2diffa.ocprestige) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.005751535
r2diffb.ocprestige <- (PE.modelb2.ocprestige$est[PE.modelb2.ocprestige$op == "r2"] - PE.modelb1.ocprestige$est[PE.modelb1.ocprestige$op == "r2"])
print(r2diffb.ocprestige) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.002936041
modela1.inc <- 'Zinc ~ sex1 + Zgcse'
modela1.incfit <- sem(modela1.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 130.920
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -16499.970
## Loglikelihood unrestricted model (H1) -16499.970
##
## Akaike (AIC) 33017.940
## Bayesian (BIC) 33078.940
## Sample-size adjusted Bayesian (SABIC) 33050.340
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.388 0.046 8.359 0.000 0.297 0.479
## Zgcse 0.192 0.024 8.035 0.000 0.145 0.239
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.132 0.028 -4.751 0.000 -0.187 -0.078
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.932 0.030 30.668 0.000 0.873 0.992
## sex1 0.249 0.004 56.957 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zinc 0.070
standardizedsolution(modela1.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.194 0.023 8.561 0 0.149 0.238
## 2 Zinc ~ Zgcse 0.192 0.023 8.232 0 0.146 0.237
## 3 Zinc ~~ Zinc 0.930 0.011 80.927 0 0.907 0.952
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zinc ~1 -0.132 0.028 -4.791 0 -0.186 -0.078
## 8 sex1 ~1 0.950 0.015 63.510 0 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1 -0.024 0.024
modela2.inc <- 'Zinc ~ sex1 + Zgcse + sex.gcse'
modela2.incfit <- sem(modela2.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 131.905
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -21198.154
## Loglikelihood unrestricted model (H1) -21198.154
##
## Akaike (AIC) 42424.308
## Bayesian (BIC) 42519.195
## Sample-size adjusted Bayesian (SABIC) 42474.707
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.387 0.046 8.322 0.000 0.295 0.478
## Zgcse 0.211 0.031 6.883 0.000 0.151 0.271
## sex.gcse -0.049 0.049 -0.993 0.321 -0.144 0.047
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.131 0.028 -4.721 0.000 -0.186 -0.077
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.932 0.030 30.668 0.000 0.872 0.991
## sex1 0.249 0.004 56.955 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zinc 0.069
standardizedsolution(modela2.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.193 0.023 8.524 0.000 0.149 0.237
## 2 Zinc ~ Zgcse 0.211 0.030 6.972 0.000 0.152 0.270
## 3 Zinc ~ sex.gcse -0.034 0.034 -0.992 0.321 -0.101 0.033
## 4 Zinc ~~ Zinc 0.931 0.011 81.833 0.000 0.909 0.953
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.586 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zinc ~1 -0.131 0.028 -4.760 0.000 -0.185 -0.077
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.inc <- 'Zinc ~ SESscore + Zgcse'
modelb1.incfit <- sem(modelb1.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 65.546
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19612.377
## Loglikelihood unrestricted model (H1) -19612.377
##
## Akaike (AIC) 39242.754
## Bayesian (BIC) 39303.754
## Sample-size adjusted Bayesian (SABIC) 39275.154
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## SESscore 0.051 0.028 1.799 0.072 -0.005 0.106
## Zgcse 0.172 0.027 6.346 0.000 0.119 0.225
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.425 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.014 0.023 0.589 0.556 -0.031 0.059
## SESscore -0.034 0.012 -2.916 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.965 0.031 30.668 0.000 0.904 1.027
## SESscore 0.874 0.016 56.321 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zinc 0.039
standardizedsolution(modelb1.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ SESscore 0.047 0.026 1.802 0.072 -0.004 0.099
## 2 Zinc ~ Zgcse 0.172 0.027 6.457 0.000 0.120 0.224
## 3 Zinc ~~ Zinc 0.961 0.009 102.310 0.000 0.942 0.979
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.310 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zinc ~1 0.013 0.023 0.589 0.556 -0.031 0.058
## 8 SESscore ~1 -0.036 0.013 -2.916 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.inc <- 'Zinc ~ SESscore + Zgcse + SES.gcse'
modelb2.incfit <- sem(modelb2.inc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.incfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 66.287
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -28330.197
## Loglikelihood unrestricted model (H1) -28330.197
##
## Akaike (AIC) 56688.394
## Bayesian (BIC) 56783.282
## Sample-size adjusted Bayesian (SABIC) 56738.793
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## SESscore 0.050 0.028 1.760 0.078 -0.006 0.105
## Zgcse 0.176 0.027 6.402 0.000 0.122 0.230
## SES.gcse 0.022 0.026 0.861 0.389 -0.028 0.073
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.425 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.118 0.264 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.664 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.005 0.025 0.208 0.835 -0.044 0.054
## SESscore -0.034 0.012 -2.916 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.802 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.965 0.031 30.667 0.000 0.903 1.026
## SESscore 0.874 0.016 56.321 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zinc 0.040
standardizedsolution(modelb2.incfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zinc ~ SESscore 0.046 0.026 1.762 0.078 -0.005 0.098
## 2 Zinc ~ Zgcse 0.176 0.027 6.518 0.000 0.123 0.228
## 3 Zinc ~ SES.gcse 0.021 0.025 0.861 0.389 -0.027 0.070
## 4 Zinc ~~ Zinc 0.960 0.010 100.756 0.000 0.941 0.978
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.310 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.118 0.264 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.882 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zinc ~1 0.005 0.025 0.208 0.835 -0.044 0.054
## 12 SESscore ~1 -0.036 0.013 -2.915 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.004 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.inc <- parameterEstimates(modela1.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.388 0.046 8.359 0 0.297 0.479
## 2 Zinc ~ Zgcse 0.192 0.024 8.035 0 0.145 0.239
## 3 Zinc ~~ Zinc 0.932 0.030 30.668 0 0.873 0.992
## 4 sex1 ~~ sex1 0.249 0.004 56.957 0 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0 0.965 1.034
## 7 Zinc ~1 -0.132 0.028 -4.751 0 -0.187 -0.078
## 8 sex1 ~1 0.474 0.006 76.503 0 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1 -0.024 0.024
## 10 Zinc r2 Zinc 0.070 NA NA NA NA NA
PE.modela1.inc$est[PE.modela1.inc$op == "r2"]
## [1] 0.07029591
(PE.modela2.inc <- parameterEstimates(modela2.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ sex1 0.387 0.046 8.322 0.000 0.295 0.478
## 2 Zinc ~ Zgcse 0.211 0.031 6.883 0.000 0.151 0.271
## 3 Zinc ~ sex.gcse -0.049 0.049 -0.993 0.321 -0.144 0.047
## 4 Zinc ~~ Zinc 0.932 0.030 30.668 0.000 0.872 0.991
## 5 sex1 ~~ sex1 0.249 0.004 56.955 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zinc ~1 -0.131 0.028 -4.721 0.000 -0.186 -0.077
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zinc r2 Zinc 0.069 NA NA NA NA NA
PE.modela2.inc$est[PE.modela2.inc$op == "r2"]
## [1] 0.0690365
(PE.modelb1.inc <- parameterEstimates(modelb1.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ SESscore 0.051 0.028 1.799 0.072 -0.005 0.106
## 2 Zinc ~ Zgcse 0.172 0.027 6.346 0.000 0.119 0.225
## 3 Zinc ~~ Zinc 0.965 0.031 30.668 0.000 0.904 1.027
## 4 SESscore ~~ SESscore 0.874 0.016 56.321 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.425 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zinc ~1 0.014 0.023 0.589 0.556 -0.031 0.059
## 8 SESscore ~1 -0.034 0.012 -2.916 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zinc r2 Zinc 0.039 NA NA NA NA NA
PE.modelb1.inc$est[PE.modelb1.inc$op == "r2"]
## [1] 0.0394635
(PE.modelb2.inc <- parameterEstimates(modelb2.incfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zinc ~ SESscore 0.050 0.028 1.760 0.078 -0.006 0.105
## 2 Zinc ~ Zgcse 0.176 0.027 6.402 0.000 0.122 0.230
## 3 Zinc ~ SES.gcse 0.022 0.026 0.861 0.389 -0.028 0.073
## 4 Zinc ~~ Zinc 0.965 0.031 30.667 0.000 0.903 1.026
## 5 SESscore ~~ SESscore 0.874 0.016 56.321 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.425 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.118 0.264 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.664 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
## 11 Zinc ~1 0.005 0.025 0.208 0.835 -0.044 0.054
## 12 SESscore ~1 -0.034 0.012 -2.916 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.802 0.000 0.420 0.467
## 15 Zinc r2 Zinc 0.040 NA NA NA NA NA
PE.modelb2.inc$est[PE.modelb2.inc$op == "r2"]
## [1] 0.04025784
r2diffa.inc <- (PE.modela2.inc$est[PE.modela2.inc$op == "r2"] - PE.modela1.inc$est[PE.modela1.inc$op == "r2"])
print(r2diffa.inc) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] -0.001259405
r2diffb.inc <- (PE.modelb2.inc$est[PE.modelb2.inc$op == "r2"] - PE.modelb1.inc$est[PE.modelb1.inc$op == "r2"])
print(r2diffb.inc) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.0007943386
model1.mon <- 'Zmon ~ sex1 + SESscore'
model1.monfit <- sem(model1.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(model1.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 56.036
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18452.108
## Loglikelihood unrestricted model (H1) -18452.108
##
## Akaike (AIC) 36922.215
## Bayesian (BIC) 36983.215
## Sample-size adjusted Bayesian (SABIC) 36954.615
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.232 0.034 -6.887 0.000 -0.298 -0.166
## SESscore -0.047 0.018 -2.652 0.008 -0.082 -0.012
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.013 0.006 2.288 0.022 0.002 0.025
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.093 0.021 4.422 0.000 0.052 0.134
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.029 0.012 -2.514 0.012 -0.052 -0.006
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.985 0.023 42.777 0.000 0.939 1.030
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.873 0.015 56.387 0.000 0.842 0.903
##
## R-Square:
## Estimate
## Zmon 0.016
standardizedsolution(model1.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.116 0.017 -6.945 0.000 -0.149 -0.083
## 2 Zmon ~ SESscore -0.044 0.017 -2.654 0.008 -0.077 -0.012
## 3 Zmon ~~ Zmon 0.984 0.004 237.936 0.000 0.976 0.992
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ SESscore 0.029 0.013 2.290 0.022 0.004 0.053
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 Zmon ~1 0.093 0.021 4.441 0.000 0.052 0.133
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 SESscore ~1 -0.032 0.013 -2.514 0.012 -0.056 -0.007
modela1.mon <- 'Zmon ~ sex1 + Zgcse'
modela1.monfit <- sem(modela1.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 58.653
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19060.395
## Loglikelihood unrestricted model (H1) -19060.395
##
## Akaike (AIC) 38138.791
## Bayesian (BIC) 38199.790
## Sample-size adjusted Bayesian (SABIC) 38171.190
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.238 0.034 -7.070 0.000 -0.304 -0.172
## Zgcse 0.054 0.017 3.107 0.002 0.020 0.088
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.081 0.021 3.813 0.000 0.039 0.122
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.984 0.023 42.779 0.000 0.939 1.029
## sex1 0.249 0.004 56.957 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zmon 0.018
standardizedsolution(modela1.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.119 0.017 -7.136 0.000 -0.151 -0.086
## 2 Zmon ~ Zgcse 0.054 0.017 3.114 0.002 0.020 0.088
## 3 Zmon ~~ Zmon 0.982 0.005 215.636 0.000 0.973 0.991
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zmon ~1 0.081 0.021 3.824 0.000 0.039 0.122
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.mon <- 'Zmon ~ sex1 + Zgcse + sex.gcse'
modela2.monfit <- sem(modela2.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 60.556
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23758.120
## Loglikelihood unrestricted model (H1) -23758.120
##
## Akaike (AIC) 47544.240
## Bayesian (BIC) 47639.128
## Sample-size adjusted Bayesian (SABIC) 47594.640
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.228 0.034 -6.602 0.000 -0.295 -0.160
## Zgcse 0.073 0.022 3.283 0.001 0.030 0.117
## sex.gcse -0.049 0.035 -1.379 0.168 -0.118 0.021
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.002 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.077 0.021 3.601 0.000 0.035 0.119
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.983 0.023 42.778 0.000 0.938 1.028
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zmon 0.017
standardizedsolution(modela2.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.114 0.017 -6.658 0.000 -0.147 -0.080
## 2 Zmon ~ Zgcse 0.073 0.022 3.286 0.001 0.030 0.117
## 3 Zmon ~ sex.gcse -0.034 0.025 -1.378 0.168 -0.083 0.014
## 4 Zmon ~~ Zmon 0.983 0.004 226.516 0.000 0.975 0.992
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.584 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zmon ~1 0.077 0.021 3.612 0.000 0.035 0.119
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.mon <- 'Zmon ~ SESscore + Zgcse'
modelb1.monfit <- sem(modelb1.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 32.000
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -22153.442
## Loglikelihood unrestricted model (H1) -22153.442
##
## Akaike (AIC) 44324.883
## Bayesian (BIC) 44385.883
## Sample-size adjusted Bayesian (SABIC) 44357.283
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## SESscore -0.097 0.020 -4.803 0.000 -0.137 -0.057
## Zgcse 0.097 0.020 4.930 0.000 0.059 0.136
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.415 0.000 0.421 0.472
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon -0.014 0.017 -0.852 0.394 -0.047 0.019
## SESscore -0.034 0.012 -2.911 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.991 0.023 42.773 0.000 0.946 1.036
## SESscore 0.874 0.016 56.330 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zmon 0.009
standardizedsolution(modelb1.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ SESscore -0.091 0.019 -4.822 0.000 -0.128 -0.054
## 2 Zmon ~ Zgcse 0.097 0.020 4.953 0.000 0.059 0.136
## 3 Zmon ~~ Zmon 0.991 0.003 304.307 0.000 0.984 0.997
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.276 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zmon ~1 -0.014 0.017 -0.852 0.394 -0.047 0.019
## 8 SESscore ~1 -0.036 0.013 -2.910 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.mon <- 'Zmon ~ SESscore + Zgcse + SES.gcse'
modelb2.monfit <- sem(modelb2.mon, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.monfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 41.592
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30866.836
## Loglikelihood unrestricted model (H1) -30866.836
##
## Akaike (AIC) 61761.672
## Bayesian (BIC) 61856.560
## Sample-size adjusted Bayesian (SABIC) 61812.072
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## SESscore -0.085 0.021 -4.147 0.000 -0.125 -0.045
## Zgcse 0.094 0.020 4.772 0.000 0.056 0.133
## SES.gcse -0.058 0.019 -3.099 0.002 -0.094 -0.021
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.416 0.000 0.421 0.472
## SES.gcse -0.013 0.011 -1.122 0.262 -0.035 0.009
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.678 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.010 0.019 0.543 0.587 -0.026 0.047
## SESscore -0.034 0.012 -2.911 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.806 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.988 0.023 42.772 0.000 0.943 1.034
## SESscore 0.874 0.016 56.329 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.376 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zmon 0.012
standardizedsolution(modelb2.monfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zmon ~ SESscore -0.080 0.019 -4.157 0.000 -0.117 -0.042
## 2 Zmon ~ Zgcse 0.094 0.020 4.794 0.000 0.056 0.133
## 3 Zmon ~ SES.gcse -0.055 0.018 -3.106 0.002 -0.090 -0.020
## 4 Zmon ~~ Zmon 0.988 0.004 259.151 0.000 0.980 0.995
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.280 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.122 0.262 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.897 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zmon ~1 0.010 0.019 0.543 0.587 -0.026 0.047
## 12 SESscore ~1 -0.036 0.013 -2.911 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.462 0.013 35.008 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.mon <- parameterEstimates(modela1.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.238 0.034 -7.070 0.000 -0.304 -0.172
## 2 Zmon ~ Zgcse 0.054 0.017 3.107 0.002 0.020 0.088
## 3 Zmon ~~ Zmon 0.984 0.023 42.779 0.000 0.939 1.029
## 4 sex1 ~~ sex1 0.249 0.004 56.957 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zmon ~1 0.081 0.021 3.813 0.000 0.039 0.122
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zmon r2 Zmon 0.018 NA NA NA NA NA
PE.modela1.mon$est[PE.modela1.mon$op == "r2"]
## [1] 0.01768206
(PE.modela2.mon <- parameterEstimates(modela2.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ sex1 -0.228 0.034 -6.602 0.000 -0.295 -0.160
## 2 Zmon ~ Zgcse 0.073 0.022 3.283 0.001 0.030 0.117
## 3 Zmon ~ sex.gcse -0.049 0.035 -1.379 0.168 -0.118 0.021
## 4 Zmon ~~ Zmon 0.983 0.023 42.778 0.000 0.938 1.028
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.002 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zmon ~1 0.077 0.021 3.601 0.000 0.035 0.119
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zmon r2 Zmon 0.017 NA NA NA NA NA
PE.modela2.mon$est[PE.modela2.mon$op == "r2"]
## [1] 0.01651096
(PE.modelb1.mon <- parameterEstimates(modelb1.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ SESscore -0.097 0.020 -4.803 0.000 -0.137 -0.057
## 2 Zmon ~ Zgcse 0.097 0.020 4.930 0.000 0.059 0.136
## 3 Zmon ~~ Zmon 0.991 0.023 42.773 0.000 0.946 1.036
## 4 SESscore ~~ SESscore 0.874 0.016 56.330 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.415 0.000 0.421 0.472
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zmon ~1 -0.014 0.017 -0.852 0.394 -0.047 0.019
## 8 SESscore ~1 -0.034 0.012 -2.911 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zmon r2 Zmon 0.009 NA NA NA NA NA
PE.modelb1.mon$est[PE.modelb1.mon$op == "r2"]
## [1] 0.009271553
(PE.modelb2.mon <- parameterEstimates(modelb2.monfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zmon ~ SESscore -0.085 0.021 -4.147 0.000 -0.125 -0.045
## 2 Zmon ~ Zgcse 0.094 0.020 4.772 0.000 0.056 0.133
## 3 Zmon ~ SES.gcse -0.058 0.019 -3.099 0.002 -0.094 -0.021
## 4 Zmon ~~ Zmon 0.988 0.023 42.772 0.000 0.943 1.034
## 5 SESscore ~~ SESscore 0.874 0.016 56.329 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.416 0.000 0.421 0.472
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.122 0.262 -0.035 0.009
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.678 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.376 0.000 0.893 0.957
## 11 Zmon ~1 0.010 0.019 0.543 0.587 -0.026 0.047
## 12 SESscore ~1 -0.034 0.012 -2.911 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.806 0.000 0.420 0.467
## 15 Zmon r2 Zmon 0.012 NA NA NA NA NA
PE.modelb2.mon$est[PE.modelb2.mon$op == "r2"]
## [1] 0.01228161
r2diffa.mon <- (PE.modela2.mon$est[PE.modela2.mon$op == "r2"] - PE.modela1.mon$est[PE.modela1.mon$op == "r2"])
print(r2diffa.mon) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] -0.001171099
r2diffb.mon <- (PE.modelb2.mon$est[PE.modelb2.mon$op == "r2"] - PE.modelb1.mon$est[PE.modelb1.mon$op == "r2"])
print(r2diffb.mon) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.003010057
modela1.fina <- 'Zfina ~ sex1 + Zgcse'
modela1.finafit <- sem(modela1.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 3.181
## Degrees of freedom 2
## P-value 0.204
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19090.969
## Loglikelihood unrestricted model (H1) -19090.969
##
## Akaike (AIC) 38199.938
## Bayesian (BIC) 38260.938
## Sample-size adjusted Bayesian (SABIC) 38232.338
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.059 0.034 1.732 0.083 -0.008 0.125
## Zgcse 0.007 0.017 0.406 0.685 -0.027 0.041
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.024 0.021 -1.130 0.258 -0.066 0.018
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.999 0.023 42.790 0.000 0.953 1.045
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zfina 0.001
standardizedsolution(modela1.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.029 0.017 1.733 0.083 -0.004 0.063
## 2 Zfina ~ Zgcse 0.007 0.017 0.406 0.685 -0.027 0.041
## 3 Zfina ~~ Zfina 0.999 0.001 1001.293 0.000 0.997 1.001
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zfina ~1 -0.024 0.021 -1.131 0.258 -0.066 0.018
## 8 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.fina <- 'Zfina ~ sex1 + Zgcse + sex.gcse'
modela2.finafit <- sem(modela2.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 3.655
## Degrees of freedom 3
## P-value 0.301
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23789.408
## Loglikelihood unrestricted model (H1) -23789.408
##
## Akaike (AIC) 47606.817
## Bayesian (BIC) 47701.705
## Sample-size adjusted Bayesian (SABIC) 47657.216
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.064 0.035 1.841 0.066 -0.004 0.132
## Zgcse 0.017 0.022 0.749 0.454 -0.027 0.061
## sex.gcse -0.025 0.036 -0.689 0.491 -0.095 0.045
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.026 0.022 -1.210 0.226 -0.068 0.016
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.999 0.023 42.790 0.000 0.953 1.044
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zfina 0.001
standardizedsolution(modela2.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.032 0.017 1.842 0.065 -0.002 0.066
## 2 Zfina ~ Zgcse 0.017 0.022 0.749 0.454 -0.027 0.061
## 3 Zfina ~ sex.gcse -0.017 0.025 -0.689 0.491 -0.066 0.032
## 4 Zfina ~~ Zfina 0.999 0.001 790.092 0.000 0.996 1.001
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.585 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zfina ~1 -0.026 0.022 -1.211 0.226 -0.068 0.016
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.fina <- 'Zfina ~ SESscore + Zgcse'
modelb1.finafit <- sem(modelb1.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 14.594
## Degrees of freedom 2
## P-value 0.001
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -22164.982
## Loglikelihood unrestricted model (H1) -22164.982
##
## Akaike (AIC) 44347.965
## Bayesian (BIC) 44408.964
## Sample-size adjusted Bayesian (SABIC) 44380.364
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## SESscore -0.077 0.020 -3.800 0.000 -0.117 -0.037
## Zgcse 0.043 0.020 2.179 0.029 0.004 0.082
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.419 0.000 0.422 0.472
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.004 0.017 -0.258 0.796 -0.037 0.029
## SESscore -0.034 0.012 -2.903 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.996 0.023 42.787 0.000 0.950 1.041
## SESscore 0.874 0.016 56.325 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zfina 0.004
standardizedsolution(modelb1.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ SESscore -0.072 0.019 -3.810 0.000 -0.109 -0.035
## 2 Zfina ~ Zgcse 0.043 0.020 2.180 0.029 0.004 0.082
## 3 Zfina ~~ Zfina 0.996 0.002 468.693 0.000 0.992 1.000
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.292 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zfina ~1 -0.004 0.017 -0.258 0.796 -0.037 0.029
## 8 SESscore ~1 -0.036 0.013 -2.902 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.fina <- 'Zfina ~ SESscore + Zgcse + SES.gcse'
modelb2.finafit <- sem(modelb2.fina, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.finafit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 12 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 14.617
## Degrees of freedom 3
## P-value 0.002
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30883.161
## Loglikelihood unrestricted model (H1) -30883.161
##
## Akaike (AIC) 61794.323
## Bayesian (BIC) 61889.211
## Sample-size adjusted Bayesian (SABIC) 61844.722
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## SESscore -0.078 0.021 -3.762 0.000 -0.118 -0.037
## Zgcse 0.043 0.020 2.183 0.029 0.004 0.082
## SES.gcse 0.003 0.019 0.151 0.880 -0.034 0.039
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.419 0.000 0.422 0.472
## SES.gcse -0.013 0.011 -1.116 0.264 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.664 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.006 0.019 -0.298 0.766 -0.042 0.031
## SESscore -0.034 0.012 -2.903 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.803 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.996 0.023 42.787 0.000 0.950 1.041
## SESscore 0.874 0.016 56.326 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zfina 0.004
standardizedsolution(modelb2.finafit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zfina ~ SESscore -0.072 0.019 -3.771 0.000 -0.110 -0.035
## 2 Zfina ~ Zgcse 0.043 0.020 2.185 0.029 0.004 0.082
## 3 Zfina ~ SES.gcse 0.003 0.018 0.151 0.880 -0.032 0.038
## 4 Zfina ~~ Zfina 0.996 0.002 461.309 0.000 0.992 1.000
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.291 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.117 0.264 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.882 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zfina ~1 -0.006 0.019 -0.298 0.766 -0.042 0.031
## 12 SESscore ~1 -0.036 0.013 -2.902 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.005 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.fina <- parameterEstimates(modela1.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.059 0.034 1.732 0.083 -0.008 0.125
## 2 Zfina ~ Zgcse 0.007 0.017 0.406 0.685 -0.027 0.041
## 3 Zfina ~~ Zfina 0.999 0.023 42.790 0.000 0.953 1.045
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zfina ~1 -0.024 0.021 -1.130 0.258 -0.066 0.018
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zfina r2 Zfina 0.001 NA NA NA NA NA
PE.modela1.fina$est[PE.modela1.fina$op == "r2"]
## [1] 0.0008895165
(PE.modela2.fina <- parameterEstimates(modela2.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ sex1 0.064 0.035 1.841 0.066 -0.004 0.132
## 2 Zfina ~ Zgcse 0.017 0.022 0.749 0.454 -0.027 0.061
## 3 Zfina ~ sex.gcse -0.025 0.036 -0.689 0.491 -0.095 0.045
## 4 Zfina ~~ Zfina 0.999 0.023 42.790 0.000 0.953 1.044
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zfina ~1 -0.026 0.022 -1.210 0.226 -0.068 0.016
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zfina r2 Zfina 0.001 NA NA NA NA NA
PE.modela2.fina$est[PE.modela2.fina$op == "r2"]
## [1] 0.001180469
(PE.modelb1.fina <- parameterEstimates(modelb1.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ SESscore -0.077 0.020 -3.800 0.000 -0.117 -0.037
## 2 Zfina ~ Zgcse 0.043 0.020 2.179 0.029 0.004 0.082
## 3 Zfina ~~ Zfina 0.996 0.023 42.787 0.000 0.950 1.041
## 4 SESscore ~~ SESscore 0.874 0.016 56.325 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.419 0.000 0.422 0.472
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zfina ~1 -0.004 0.017 -0.258 0.796 -0.037 0.029
## 8 SESscore ~1 -0.034 0.012 -2.903 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zfina r2 Zfina 0.004 NA NA NA NA NA
PE.modelb1.fina$est[PE.modelb1.fina$op == "r2"]
## [1] 0.00407102
(PE.modelb2.fina <- parameterEstimates(modelb2.finafit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zfina ~ SESscore -0.078 0.021 -3.762 0.000 -0.118 -0.037
## 2 Zfina ~ Zgcse 0.043 0.020 2.183 0.029 0.004 0.082
## 3 Zfina ~ SES.gcse 0.003 0.019 0.151 0.880 -0.034 0.039
## 4 Zfina ~~ Zfina 0.996 0.023 42.787 0.000 0.950 1.041
## 5 SESscore ~~ SESscore 0.874 0.016 56.326 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.419 0.000 0.422 0.472
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.116 0.264 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.664 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
## 11 Zfina ~1 -0.006 0.019 -0.298 0.766 -0.042 0.031
## 12 SESscore ~1 -0.034 0.012 -2.903 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.803 0.000 0.420 0.467
## 15 Zfina r2 Zfina 0.004 NA NA NA NA NA
PE.modelb2.fina$est[PE.modelb2.fina$op == "r2"]
## [1] 0.004113188
r2diffa.fina <- (PE.modela2.fina$est[PE.modela2.fina$op == "r2"] - PE.modela1.fina$est[PE.modela1.fina$op == "r2"])
print(r2diffa.fina) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.0002909522
r2diffb.fina <- (PE.modelb2.fina$est[PE.modelb2.fina$op == "r2"] - PE.modelb1.fina$est[PE.modelb1.fina$op == "r2"])
print(r2diffb.fina) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 4.216797e-05
modela1.wellb <- 'Zwellb ~ sex1 + Zgcse'
modela1.wellbfit <- sem(modela1.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 109.405
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19168.400
## Loglikelihood unrestricted model (H1) -19168.400
##
## Akaike (AIC) 38354.799
## Bayesian (BIC) 38415.798
## Sample-size adjusted Bayesian (SABIC) 38387.199
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.265 0.033 8.005 0.000 0.200 0.330
## Zgcse 0.115 0.017 6.768 0.000 0.082 0.149
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.124 0.021 -6.002 0.000 -0.165 -0.084
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.971 0.022 43.324 0.000 0.927 1.015
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zwellb 0.029
standardizedsolution(modela1.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.132 0.016 8.085 0 0.100 0.164
## 2 Zwellb ~ Zgcse 0.115 0.017 6.819 0 0.082 0.148
## 3 Zwellb ~~ Zwellb 0.971 0.005 178.603 0 0.960 0.982
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zwellb ~1 -0.124 0.021 -6.044 0 -0.165 -0.084
## 8 sex1 ~1 0.950 0.015 63.510 0 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1 -0.024 0.024
modela2.wellb <- 'Zwellb ~ sex1 + Zgcse + sex.gcse'
modela2.wellbfit <- sem(modela2.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 111.789
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23865.884
## Loglikelihood unrestricted model (H1) -23865.884
##
## Akaike (AIC) 47759.768
## Bayesian (BIC) 47854.656
## Sample-size adjusted Bayesian (SABIC) 47810.167
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.276 0.034 8.154 0.000 0.210 0.342
## Zgcse 0.137 0.022 6.226 0.000 0.094 0.180
## sex.gcse -0.054 0.035 -1.545 0.122 -0.122 0.014
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.129 0.021 -6.151 0.000 -0.170 -0.088
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.970 0.022 43.324 0.000 0.927 1.014
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zwellb 0.030
standardizedsolution(modela2.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.138 0.017 8.248 0.000 0.105 0.170
## 2 Zwellb ~ Zgcse 0.137 0.022 6.268 0.000 0.094 0.179
## 3 Zwellb ~ sex.gcse -0.038 0.024 -1.546 0.122 -0.085 0.010
## 4 Zwellb ~~ Zwellb 0.970 0.006 173.675 0.000 0.959 0.981
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.585 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zwellb ~1 -0.129 0.021 -6.200 0.000 -0.169 -0.088
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.wellb <- 'Zwellb ~ SESscore + Zgcse'
modelb1.wellbfit <- sem(modelb1.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 46.942
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -22279.351
## Loglikelihood unrestricted model (H1) -22279.351
##
## Akaike (AIC) 44576.701
## Bayesian (BIC) 44637.701
## Sample-size adjusted Bayesian (SABIC) 44609.101
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## SESscore 0.021 0.020 1.038 0.299 -0.018 0.059
## Zgcse 0.107 0.019 5.492 0.000 0.069 0.145
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.023 0.017 -1.357 0.175 -0.055 0.010
## SESscore -0.034 0.012 -2.916 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.987 0.023 43.325 0.000 0.943 1.032
## SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zwellb 0.014
standardizedsolution(modelb1.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ SESscore 0.019 0.019 1.038 0.299 -0.017 0.056
## 2 Zwellb ~ Zgcse 0.107 0.019 5.525 0.000 0.069 0.145
## 3 Zwellb ~~ Zwellb 0.986 0.004 247.977 0.000 0.978 0.994
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.312 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zwellb ~1 -0.023 0.017 -1.358 0.174 -0.055 0.010
## 8 SESscore ~1 -0.036 0.013 -2.915 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.wellb <- 'Zwellb ~ SESscore + Zgcse + SES.gcse'
modelb2.wellbfit <- sem(modelb2.wellb, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.wellbfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 48.553
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30996.736
## Loglikelihood unrestricted model (H1) -30996.736
##
## Akaike (AIC) 62021.472
## Bayesian (BIC) 62116.360
## Sample-size adjusted Bayesian (SABIC) 62071.871
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## SESscore 0.016 0.020 0.794 0.427 -0.024 0.056
## Zgcse 0.108 0.020 5.541 0.000 0.070 0.146
## SES.gcse 0.023 0.018 1.269 0.204 -0.013 0.059
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.117 0.264 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.661 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.032 0.018 -1.767 0.077 -0.068 0.004
## SESscore -0.034 0.012 -2.915 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.801 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.987 0.023 43.324 0.000 0.942 1.032
## SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.380 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zwellb 0.013
standardizedsolution(modelb2.wellbfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zwellb ~ SESscore 0.015 0.019 0.794 0.427 -0.022 0.052
## 2 Zwellb ~ Zgcse 0.108 0.019 5.573 0.000 0.070 0.146
## 3 Zwellb ~ SES.gcse 0.022 0.018 1.269 0.204 -0.012 0.057
## 4 Zwellb ~~ Zwellb 0.987 0.004 256.587 0.000 0.979 0.994
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.313 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.117 0.264 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.879 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zwellb ~1 -0.032 0.018 -1.768 0.077 -0.068 0.004
## 12 SESscore ~1 -0.036 0.013 -2.915 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.003 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.wellb <- parameterEstimates(modela1.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.265 0.033 8.005 0 0.200 0.330
## 2 Zwellb ~ Zgcse 0.115 0.017 6.768 0 0.082 0.149
## 3 Zwellb ~~ Zwellb 0.971 0.022 43.324 0 0.927 1.015
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0 0.965 1.034
## 7 Zwellb ~1 -0.124 0.021 -6.002 0 -0.165 -0.084
## 8 sex1 ~1 0.474 0.006 76.503 0 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1 -0.024 0.024
## 10 Zwellb r2 Zwellb 0.029 NA NA NA NA NA
PE.modela1.wellb$est[PE.modela1.wellb$op == "r2"]
## [1] 0.02915231
(PE.modela2.wellb <- parameterEstimates(modela2.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ sex1 0.276 0.034 8.154 0.000 0.210 0.342
## 2 Zwellb ~ Zgcse 0.137 0.022 6.226 0.000 0.094 0.180
## 3 Zwellb ~ sex.gcse -0.054 0.035 -1.545 0.122 -0.122 0.014
## 4 Zwellb ~~ Zwellb 0.970 0.022 43.324 0.000 0.927 1.014
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zwellb ~1 -0.129 0.021 -6.151 0.000 -0.170 -0.088
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zwellb r2 Zwellb 0.030 NA NA NA NA NA
PE.modela2.wellb$est[PE.modela2.wellb$op == "r2"]
## [1] 0.0302282
(PE.modelb1.wellb <- parameterEstimates(modelb1.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ SESscore 0.021 0.020 1.038 0.299 -0.018 0.059
## 2 Zwellb ~ Zgcse 0.107 0.019 5.492 0.000 0.069 0.145
## 3 Zwellb ~~ Zwellb 0.987 0.023 43.325 0.000 0.943 1.032
## 4 SESscore ~~ SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zwellb ~1 -0.023 0.017 -1.357 0.175 -0.055 0.010
## 8 SESscore ~1 -0.034 0.012 -2.916 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zwellb r2 Zwellb 0.014 NA NA NA NA NA
PE.modelb1.wellb$est[PE.modelb1.wellb$op == "r2"]
## [1] 0.01378128
(PE.modelb2.wellb <- parameterEstimates(modelb2.wellbfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zwellb ~ SESscore 0.016 0.020 0.794 0.427 -0.024 0.056
## 2 Zwellb ~ Zgcse 0.108 0.020 5.541 0.000 0.070 0.146
## 3 Zwellb ~ SES.gcse 0.023 0.018 1.269 0.204 -0.013 0.059
## 4 Zwellb ~~ Zwellb 0.987 0.023 43.324 0.000 0.942 1.032
## 5 SESscore ~~ SESscore 0.874 0.016 56.320 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.426 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.117 0.264 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.661 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.380 0.000 0.893 0.957
## 11 Zwellb ~1 -0.032 0.018 -1.767 0.077 -0.068 0.004
## 12 SESscore ~1 -0.034 0.012 -2.915 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.801 0.000 0.420 0.467
## 15 Zwellb r2 Zwellb 0.013 NA NA NA NA NA
PE.modelb2.wellb$est[PE.modelb2.wellb$op == "r2"]
## [1] 0.01333689
r2diffa.wellb <- (PE.modela2.wellb$est[PE.modela2.wellb$op == "r2"] - PE.modela1.wellb$est[PE.modela1.wellb$op == "r2"])
print(r2diffa.wellb) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.001075893
r2diffb.wellb <- (PE.modelb2.wellb$est[PE.modelb2.wellb$op == "r2"] - PE.modelb1.wellb$est[PE.modelb1.wellb$op == "r2"])
print(r2diffb.wellb) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] -0.0004443923
modela1.anx <- 'Zanx ~ sex1 + Zgcse'
modela1.anxfit <- sem(modela1.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 90.926
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18716.484
## Loglikelihood unrestricted model (H1) -18716.484
##
## Akaike (AIC) 37450.968
## Bayesian (BIC) 37511.967
## Sample-size adjusted Bayesian (SABIC) 37483.368
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.334 0.035 -9.556 0.000 -0.402 -0.265
## Zgcse -0.011 0.018 -0.595 0.552 -0.045 0.024
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.126 0.021 5.850 0.000 0.083 0.168
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.974 0.024 41.406 0.000 0.927 1.020
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zanx 0.028
standardizedsolution(modela1.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.167 0.017 -9.730 0.000 -0.200 -0.133
## 2 Zanx ~ Zgcse -0.011 0.018 -0.595 0.552 -0.045 0.024
## 3 Zanx ~~ Zanx 0.972 0.006 171.166 0.000 0.961 0.983
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zanx ~1 0.125 0.021 5.895 0.000 0.084 0.167
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.anx <- 'Zanx ~ sex1 + Zgcse + sex.gcse'
modela2.anxfit <- sem(modela2.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 21 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 91.438
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23414.904
## Loglikelihood unrestricted model (H1) -23414.904
##
## Akaike (AIC) 46857.809
## Bayesian (BIC) 46952.696
## Sample-size adjusted Bayesian (SABIC) 46908.208
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.339 0.036 -9.480 0.000 -0.410 -0.269
## Zgcse -0.020 0.023 -0.910 0.363 -0.065 0.024
## sex.gcse 0.026 0.037 0.715 0.475 -0.045 0.098
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.127 0.022 5.894 0.000 0.085 0.170
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.973 0.024 41.407 0.000 0.927 1.019
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zanx 0.029
standardizedsolution(modela2.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.169 0.018 -9.668 0.000 -0.204 -0.135
## 2 Zanx ~ Zgcse -0.020 0.022 -0.910 0.363 -0.065 0.024
## 3 Zanx ~ sex.gcse 0.018 0.026 0.716 0.474 -0.032 0.068
## 4 Zanx ~~ Zanx 0.971 0.006 160.635 0.000 0.959 0.983
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.584 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zanx ~1 0.127 0.021 5.944 0.000 0.085 0.169
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.anx <- 'Zanx ~ SESscore + Zgcse'
modelb1.anxfit <- sem(modelb1.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 1.307
## Degrees of freedom 2
## P-value 0.520
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -21841.013
## Loglikelihood unrestricted model (H1) -21841.013
##
## Akaike (AIC) 43700.026
## Bayesian (BIC) 43761.026
## Sample-size adjusted Bayesian (SABIC) 43732.426
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## SESscore -0.015 0.021 -0.716 0.474 -0.056 0.026
## Zgcse -0.009 0.020 -0.435 0.664 -0.049 0.031
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.423 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.002 0.017 0.141 0.888 -0.032 0.037
## SESscore -0.034 0.012 -2.914 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.999 0.024 41.407 0.000 0.952 1.047
## SESscore 0.874 0.016 56.322 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zanx 0.000
standardizedsolution(modelb1.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ SESscore -0.014 0.020 -0.716 0.474 -0.053 0.024
## 2 Zanx ~ Zgcse -0.009 0.020 -0.435 0.664 -0.049 0.031
## 3 Zanx ~~ Zanx 1.000 0.001 1432.475 0.000 0.998 1.001
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.305 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zanx ~1 0.002 0.017 0.141 0.888 -0.032 0.037
## 8 SESscore ~1 -0.036 0.013 -2.914 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.anx <- 'Zanx ~ SESscore + Zgcse + SES.gcse'
modelb2.anxfit <- sem(modelb2.anx, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.anxfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 9.845
## Degrees of freedom 3
## P-value 0.020
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30554.935
## Loglikelihood unrestricted model (H1) -30554.935
##
## Akaike (AIC) 61137.869
## Bayesian (BIC) 61232.757
## Sample-size adjusted Bayesian (SABIC) 61188.269
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## SESscore -0.004 0.021 -0.170 0.865 -0.046 0.038
## Zgcse -0.012 0.021 -0.606 0.545 -0.053 0.028
## SES.gcse -0.056 0.019 -2.924 0.003 -0.093 -0.018
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.424 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.123 0.262 -0.035 0.009
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.675 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.027 0.019 1.384 0.166 -0.011 0.065
## SESscore -0.034 0.012 -2.914 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.804 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.997 0.024 41.405 0.000 0.950 1.044
## SESscore 0.874 0.016 56.321 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.377 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zanx 0.003
standardizedsolution(modelb2.anxfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zanx ~ SESscore -0.003 0.020 -0.170 0.865 -0.043 0.036
## 2 Zanx ~ Zgcse -0.012 0.021 -0.606 0.545 -0.053 0.028
## 3 Zanx ~ SES.gcse -0.054 0.018 -2.929 0.003 -0.090 -0.018
## 4 Zanx ~~ Zanx 0.997 0.002 527.630 0.000 0.993 1.001
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.307 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.123 0.261 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.894 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zanx ~1 0.027 0.019 1.385 0.166 -0.011 0.065
## 12 SESscore ~1 -0.036 0.013 -2.914 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.006 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.anx <- parameterEstimates(modela1.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.334 0.035 -9.556 0.000 -0.402 -0.265
## 2 Zanx ~ Zgcse -0.011 0.018 -0.595 0.552 -0.045 0.024
## 3 Zanx ~~ Zanx 0.974 0.024 41.406 0.000 0.927 1.020
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zanx ~1 0.126 0.021 5.850 0.000 0.083 0.168
## 8 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zanx r2 Zanx 0.028 NA NA NA NA NA
PE.modela1.anx$est[PE.modela1.anx$op == "r2"]
## [1] 0.02766229
(PE.modela2.anx <- parameterEstimates(modela2.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ sex1 -0.339 0.036 -9.480 0.000 -0.410 -0.269
## 2 Zanx ~ Zgcse -0.020 0.023 -0.910 0.363 -0.065 0.024
## 3 Zanx ~ sex.gcse 0.026 0.037 0.715 0.475 -0.045 0.098
## 4 Zanx ~~ Zanx 0.973 0.024 41.407 0.000 0.927 1.019
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zanx ~1 0.127 0.022 5.894 0.000 0.085 0.170
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zanx r2 Zanx 0.029 NA NA NA NA NA
PE.modela2.anx$est[PE.modela2.anx$op == "r2"]
## [1] 0.02876186
(PE.modelb1.anx <- parameterEstimates(modelb1.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ SESscore -0.015 0.021 -0.716 0.474 -0.056 0.026
## 2 Zanx ~ Zgcse -0.009 0.020 -0.435 0.664 -0.049 0.031
## 3 Zanx ~~ Zanx 0.999 0.024 41.407 0.000 0.952 1.047
## 4 SESscore ~~ SESscore 0.874 0.016 56.322 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.423 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zanx ~1 0.002 0.017 0.141 0.888 -0.032 0.037
## 8 SESscore ~1 -0.034 0.012 -2.914 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zanx r2 Zanx 0.000 NA NA NA NA NA
PE.modelb1.anx$est[PE.modelb1.anx$op == "r2"]
## [1] 0.0003987046
(PE.modelb2.anx <- parameterEstimates(modelb2.anxfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zanx ~ SESscore -0.004 0.021 -0.170 0.865 -0.046 0.038
## 2 Zanx ~ Zgcse -0.012 0.021 -0.606 0.545 -0.053 0.028
## 3 Zanx ~ SES.gcse -0.056 0.019 -2.924 0.003 -0.093 -0.018
## 4 Zanx ~~ Zanx 0.997 0.024 41.405 0.000 0.950 1.044
## 5 SESscore ~~ SESscore 0.874 0.016 56.321 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.424 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.123 0.262 -0.035 0.009
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.675 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.377 0.000 0.893 0.957
## 11 Zanx ~1 0.027 0.019 1.384 0.166 -0.011 0.065
## 12 SESscore ~1 -0.034 0.012 -2.914 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.804 0.000 0.420 0.467
## 15 Zanx r2 Zanx 0.003 NA NA NA NA NA
PE.modelb2.anx$est[PE.modelb2.anx$op == "r2"]
## [1] 0.002912923
r2diffa.anx <- (PE.modela2.anx$est[PE.modela2.anx$op == "r2"] - PE.modela1.anx$est[PE.modela1.anx$op == "r2"])
print(r2diffa.anx) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.001099575
r2diffb.anx <- (PE.modelb2.anx$est[PE.modelb2.anx$op == "r2"] - PE.modelb1.anx$est[PE.modelb1.anx$op == "r2"])
print(r2diffb.anx) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.002514218
modela1.sdq <- 'Zsdq ~ sex1 + Zgcse'
modela1.sdqfit <- sem(modela1.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 14 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 213.888
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -19117.577
## Loglikelihood unrestricted model (H1) -19117.577
##
## Akaike (AIC) 38253.154
## Bayesian (BIC) 38314.153
## Sample-size adjusted Bayesian (SABIC) 38285.554
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.194 0.033 -5.942 0.000 -0.258 -0.130
## Zgcse -0.227 0.017 -13.533 0.000 -0.260 -0.194
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.120 0.020 5.851 0.000 0.080 0.160
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.944 0.022 43.330 0.000 0.902 0.987
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zsdq 0.058
standardizedsolution(modela1.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.097 0.016 -5.967 0 -0.128 -0.065
## 2 Zsdq ~ Zgcse -0.227 0.016 -13.980 0 -0.259 -0.195
## 3 Zsdq ~~ Zsdq 0.942 0.008 123.790 0 0.927 0.956
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zsdq ~1 0.119 0.020 5.887 0 0.080 0.159
## 8 sex1 ~1 0.950 0.015 63.510 0 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1 -0.024 0.024
modela2.sdq <- 'Zsdq ~ sex1 + Zgcse + sex.gcse'
modela2.sdqfit <- sem(modela2.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 20 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 220.208
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23813.093
## Loglikelihood unrestricted model (H1) -23813.093
##
## Akaike (AIC) 47654.187
## Bayesian (BIC) 47749.075
## Sample-size adjusted Bayesian (SABIC) 47704.586
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.211 0.033 -6.342 0.000 -0.277 -0.146
## Zgcse -0.261 0.022 -12.091 0.000 -0.304 -0.219
## sex.gcse 0.086 0.034 2.515 0.012 0.019 0.153
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.126 0.021 6.129 0.000 0.086 0.167
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.943 0.022 43.330 0.000 0.900 0.985
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zsdq 0.058
standardizedsolution(modela2.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.105 0.017 -6.378 0.000 -0.138 -0.073
## 2 Zsdq ~ Zgcse -0.261 0.021 -12.359 0.000 -0.303 -0.220
## 3 Zsdq ~ sex.gcse 0.060 0.024 2.516 0.012 0.013 0.107
## 4 Zsdq ~~ Zsdq 0.942 0.008 125.472 0.000 0.927 0.956
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.249 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.584 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zsdq ~1 0.126 0.020 6.171 0.000 0.086 0.166
## 12 sex1 ~1 0.950 0.015 63.509 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.sdq <- 'Zsdq ~ SESscore + Zgcse'
modelb1.sdqfit <- sem(modelb1.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 181.064
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -22213.709
## Loglikelihood unrestricted model (H1) -22213.709
##
## Akaike (AIC) 44445.418
## Bayesian (BIC) 44506.417
## Sample-size adjusted Bayesian (SABIC) 44477.817
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## SESscore -0.030 0.020 -1.522 0.128 -0.068 0.009
## Zgcse -0.214 0.019 -11.193 0.000 -0.252 -0.177
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.427 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.044 0.016 2.727 0.006 0.013 0.076
## SESscore -0.034 0.012 -2.916 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.953 0.022 43.330 0.000 0.910 0.996
## SESscore 0.875 0.016 56.319 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zsdq 0.052
standardizedsolution(modelb1.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ SESscore -0.028 0.018 -1.522 0.128 -0.063 0.008
## 2 Zsdq ~ Zgcse -0.214 0.019 -11.463 0.000 -0.250 -0.177
## 3 Zsdq ~~ Zsdq 0.948 0.007 128.088 0.000 0.933 0.962
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.316 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zsdq ~1 0.044 0.016 2.732 0.006 0.013 0.076
## 8 SESscore ~1 -0.036 0.013 -2.916 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.sdq <- 'Zsdq ~ SESscore + Zgcse + SES.gcse'
modelb2.sdqfit <- sem(modelb2.sdq, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.sdqfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 181.150
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30931.856
## Loglikelihood unrestricted model (H1) -30931.856
##
## Akaike (AIC) 61891.713
## Bayesian (BIC) 61986.601
## Sample-size adjusted Bayesian (SABIC) 61942.112
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## SESscore -0.031 0.020 -1.549 0.121 -0.070 0.008
## Zgcse -0.214 0.019 -11.172 0.000 -0.252 -0.177
## SES.gcse 0.005 0.018 0.292 0.770 -0.030 0.040
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.427 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.118 0.263 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.665 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.042 0.018 2.348 0.019 0.007 0.077
## SESscore -0.034 0.012 -2.916 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.803 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.953 0.022 43.330 0.000 0.910 0.996
## SESscore 0.875 0.016 56.319 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zsdq 0.053
standardizedsolution(modelb2.sdqfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zsdq ~ SESscore -0.029 0.019 -1.550 0.121 -0.065 0.008
## 2 Zsdq ~ Zgcse -0.214 0.019 -11.437 0.000 -0.250 -0.177
## 3 Zsdq ~ SES.gcse 0.005 0.017 0.292 0.770 -0.029 0.039
## 4 Zsdq ~~ Zsdq 0.947 0.008 125.034 0.000 0.933 0.962
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.316 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.119 0.263 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.883 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zsdq ~1 0.042 0.018 2.349 0.019 0.007 0.077
## 12 SESscore ~1 -0.036 0.013 -2.916 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.005 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.sdq <- parameterEstimates(modela1.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.194 0.033 -5.942 0 -0.258 -0.130
## 2 Zsdq ~ Zgcse -0.227 0.017 -13.533 0 -0.260 -0.194
## 3 Zsdq ~~ Zsdq 0.944 0.022 43.330 0 0.902 0.987
## 4 sex1 ~~ sex1 0.249 0.004 56.956 0 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0 0.965 1.034
## 7 Zsdq ~1 0.120 0.020 5.851 0 0.080 0.160
## 8 sex1 ~1 0.474 0.006 76.503 0 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1 -0.024 0.024
## 10 Zsdq r2 Zsdq 0.058 NA NA NA NA NA
PE.modela1.sdq$est[PE.modela1.sdq$op == "r2"]
## [1] 0.05846109
(PE.modela2.sdq <- parameterEstimates(modela2.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ sex1 -0.211 0.033 -6.342 0.000 -0.277 -0.146
## 2 Zsdq ~ Zgcse -0.261 0.022 -12.091 0.000 -0.304 -0.219
## 3 Zsdq ~ sex.gcse 0.086 0.034 2.515 0.012 0.019 0.153
## 4 Zsdq ~~ Zsdq 0.943 0.022 43.330 0.000 0.900 0.985
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zsdq ~1 0.126 0.021 6.129 0.000 0.086 0.167
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zsdq r2 Zsdq 0.058 NA NA NA NA NA
PE.modela2.sdq$est[PE.modela2.sdq$op == "r2"]
## [1] 0.05848994
(PE.modelb1.sdq <- parameterEstimates(modelb1.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ SESscore -0.030 0.020 -1.522 0.128 -0.068 0.009
## 2 Zsdq ~ Zgcse -0.214 0.019 -11.193 0.000 -0.252 -0.177
## 3 Zsdq ~~ Zsdq 0.953 0.022 43.330 0.000 0.910 0.996
## 4 SESscore ~~ SESscore 0.875 0.016 56.319 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.427 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zsdq ~1 0.044 0.016 2.727 0.006 0.013 0.076
## 8 SESscore ~1 -0.034 0.012 -2.916 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zsdq r2 Zsdq 0.052 NA NA NA NA NA
PE.modelb1.sdq$est[PE.modelb1.sdq$op == "r2"]
## [1] 0.05213449
(PE.modelb2.sdq <- parameterEstimates(modelb2.sdqfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zsdq ~ SESscore -0.031 0.020 -1.549 0.121 -0.070 0.008
## 2 Zsdq ~ Zgcse -0.214 0.019 -11.172 0.000 -0.252 -0.177
## 3 Zsdq ~ SES.gcse 0.005 0.018 0.292 0.770 -0.030 0.040
## 4 Zsdq ~~ Zsdq 0.953 0.022 43.330 0.000 0.910 0.996
## 5 SESscore ~~ SESscore 0.875 0.016 56.319 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.427 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.118 0.263 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.665 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
## 11 Zsdq ~1 0.042 0.018 2.348 0.019 0.007 0.077
## 12 SESscore ~1 -0.034 0.012 -2.916 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.803 0.000 0.420 0.467
## 15 Zsdq r2 Zsdq 0.053 NA NA NA NA NA
PE.modelb2.sdq$est[PE.modelb2.sdq$op == "r2"]
## [1] 0.05255736
r2diffa.sdq <- (PE.modela2.sdq$est[PE.modela2.sdq$op == "r2"] - PE.modela1.sdq$est[PE.modela1.sdq$op == "r2"])
print(r2diffa.sdq) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 2.885033e-05
r2diffb.sdq <- (PE.modelb2.sdq$est[PE.modelb2.sdq$op == "r2"] - PE.modelb1.sdq$est[PE.modelb1.sdq$op == "r2"])
print(r2diffb.sdq) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.0004228697
modela1.alc <- 'Zalc ~ sex1 + Zgcse'
modela1.alcfit <- sem(modela1.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela1.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 43.625
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18371.211
## Loglikelihood unrestricted model (H1) -18371.211
##
## Akaike (AIC) 36760.421
## Bayesian (BIC) 36821.420
## Sample-size adjusted Bayesian (SABIC) 36792.821
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.232 0.036 6.366 0.000 0.161 0.304
## Zgcse 0.032 0.019 1.704 0.088 -0.005 0.069
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.094 0.023 -4.157 0.000 -0.139 -0.050
## sex1 0.474 0.006 76.504 0.000 0.462 0.486
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.986 0.025 39.806 0.000 0.937 1.035
## sex1 0.249 0.004 56.957 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zalc 0.014
standardizedsolution(modela1.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.116 0.018 6.420 0.000 0.080 0.151
## 2 Zalc ~ Zgcse 0.032 0.019 1.705 0.088 -0.005 0.069
## 3 Zalc ~~ Zalc 0.986 0.004 234.192 0.000 0.978 0.994
## 4 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zalc ~1 -0.094 0.023 -4.175 0.000 -0.138 -0.050
## 8 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modela2.alc <- 'Zalc ~ sex1 + Zgcse + sex.gcse'
modela2.alcfit <- sem(modela2.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modela2.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 2
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 43.625
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -23069.887
## Loglikelihood unrestricted model (H1) -23069.887
##
## Akaike (AIC) 46167.774
## Bayesian (BIC) 46262.661
## Sample-size adjusted Bayesian (SABIC) 46218.173
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.232 0.038 6.172 0.000 0.158 0.306
## Zgcse 0.032 0.024 1.325 0.185 -0.015 0.079
## sex.gcse 0.000 0.039 0.013 0.990 -0.075 0.076
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## Zgcse ~~
## sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.094 0.023 -4.116 0.000 -0.139 -0.049
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## sex.gcse -0.026 0.009 -3.018 0.003 -0.043 -0.009
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.986 0.025 39.806 0.000 0.937 1.035
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
##
## R-Square:
## Estimate
## Zalc 0.014
standardizedsolution(modela2.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.116 0.019 6.226 0.000 0.079 0.152
## 2 Zalc ~ Zgcse 0.032 0.024 1.325 0.185 -0.015 0.079
## 3 Zalc ~ sex.gcse 0.000 0.027 0.013 0.990 -0.053 0.053
## 4 Zalc ~~ Zalc 0.986 0.004 229.886 0.000 0.978 0.994
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse -0.053 0.012 -4.250 0.000 -0.077 -0.028
## 7 sex1 ~~ sex.gcse -0.039 0.012 -3.182 0.001 -0.064 -0.015
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ sex.gcse 0.702 0.006 111.584 0.000 0.690 0.715
## 10 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zalc ~1 -0.094 0.023 -4.134 0.000 -0.139 -0.050
## 12 sex1 ~1 0.950 0.015 63.510 0.000 0.920 0.979
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.037 0.012 -3.017 0.003 -0.062 -0.013
modelb1.alc <- 'Zalc ~ SESscore + Zgcse'
modelb1.alcfit <- sem(modelb1.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb1.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 9 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 32.815
## Degrees of freedom 2
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -21456.335
## Loglikelihood unrestricted model (H1) -21456.335
##
## Akaike (AIC) 42930.671
## Bayesian (BIC) 42991.670
## Sample-size adjusted Bayesian (SABIC) 42963.070
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## SESscore 0.119 0.022 5.442 0.000 0.076 0.161
## Zgcse -0.020 0.021 -0.948 0.343 -0.062 0.022
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.430 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.004 0.018 -0.200 0.841 -0.039 0.032
## SESscore -0.034 0.012 -2.909 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.989 0.025 39.800 0.000 0.941 1.038
## SESscore 0.875 0.016 56.316 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zalc 0.011
standardizedsolution(modelb1.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ SESscore 0.111 0.020 5.473 0.000 0.071 0.151
## 2 Zalc ~ Zgcse -0.020 0.021 -0.948 0.343 -0.062 0.022
## 3 Zalc ~~ Zalc 0.989 0.004 270.316 0.000 0.982 0.997
## 4 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ Zgcse 0.478 0.010 49.327 0.000 0.459 0.497
## 6 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 7 Zalc ~1 -0.004 0.018 -0.200 0.841 -0.039 0.032
## 8 SESscore ~1 -0.036 0.013 -2.908 0.004 -0.061 -0.012
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
modelb2.alc <- 'Zalc ~ SESscore + Zgcse + SES.gcse'
modelb2.alcfit <- sem(modelb2.alc, data = df, missing = "fiml", fixed.x = FALSE)
summary(modelb2.alcfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 14
##
## Number of observations 6488
## Number of missing patterns 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Model Test Baseline Model:
##
## Test statistic 32.817
## Degrees of freedom 3
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -30174.525
## Loglikelihood unrestricted model (H1) -30174.525
##
## Akaike (AIC) 60377.049
## Bayesian (BIC) 60471.937
## Sample-size adjusted Bayesian (SABIC) 60427.449
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## SESscore 0.118 0.022 5.289 0.000 0.075 0.162
## Zgcse -0.020 0.021 -0.946 0.344 -0.062 0.022
## SES.gcse 0.001 0.021 0.051 0.959 -0.039 0.041
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## SESscore ~~
## Zgcse 0.447 0.013 34.431 0.000 0.422 0.473
## SES.gcse -0.013 0.011 -1.119 0.263 -0.035 0.010
## Zgcse ~~
## SES.gcse -0.118 0.012 -9.663 0.000 -0.142 -0.094
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.004 0.020 -0.203 0.839 -0.043 0.035
## SESscore -0.034 0.012 -2.909 0.004 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## SES.gcse 0.444 0.012 36.803 0.000 0.420 0.467
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.989 0.025 39.800 0.000 0.941 1.038
## SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
##
## R-Square:
## Estimate
## Zalc 0.011
standardizedsolution(modelb2.alcfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 Zalc ~ SESscore 0.111 0.021 5.321 0.000 0.070 0.152
## 2 Zalc ~ Zgcse -0.020 0.021 -0.946 0.344 -0.062 0.022
## 3 Zalc ~ SES.gcse 0.001 0.020 0.051 0.959 -0.038 0.040
## 4 Zalc ~~ Zalc 0.989 0.004 264.153 0.000 0.982 0.997
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.478 0.010 49.328 0.000 0.459 0.497
## 7 SESscore ~~ SES.gcse -0.014 0.013 -1.119 0.263 -0.039 0.011
## 8 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 9 Zgcse ~~ SES.gcse -0.123 0.012 -9.881 0.000 -0.147 -0.098
## 10 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 11 Zalc ~1 -0.004 0.020 -0.203 0.839 -0.043 0.035
## 12 SESscore ~1 -0.036 0.013 -2.908 0.004 -0.061 -0.012
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.461 0.013 35.006 0.000 0.436 0.487
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.alc <- parameterEstimates(modela1.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.232 0.036 6.366 0.000 0.161 0.304
## 2 Zalc ~ Zgcse 0.032 0.019 1.704 0.088 -0.005 0.069
## 3 Zalc ~~ Zalc 0.986 0.025 39.806 0.000 0.937 1.035
## 4 sex1 ~~ sex1 0.249 0.004 56.957 0.000 0.241 0.258
## 5 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zalc ~1 -0.094 0.023 -4.157 0.000 -0.139 -0.050
## 8 sex1 ~1 0.474 0.006 76.504 0.000 0.462 0.486
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zalc r2 Zalc 0.014 NA NA NA NA NA
PE.modela1.alc$est[PE.modela1.alc$op == "r2"]
## [1] 0.01405924
(PE.modela2.alc <- parameterEstimates(modela2.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ sex1 0.232 0.038 6.172 0.000 0.158 0.306
## 2 Zalc ~ Zgcse 0.032 0.024 1.325 0.185 -0.015 0.079
## 3 Zalc ~ sex.gcse 0.000 0.039 0.013 0.990 -0.075 0.076
## 4 Zalc ~~ Zalc 0.986 0.025 39.806 0.000 0.937 1.035
## 5 sex1 ~~ sex1 0.249 0.004 56.956 0.000 0.241 0.258
## 6 sex1 ~~ Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## 7 sex1 ~~ sex.gcse -0.014 0.004 -3.175 0.001 -0.022 -0.005
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ sex.gcse 0.492 0.011 46.289 0.000 0.471 0.513
## 10 sex.gcse ~~ sex.gcse 0.492 0.009 56.956 0.000 0.475 0.509
## 11 Zalc ~1 -0.094 0.023 -4.116 0.000 -0.139 -0.049
## 12 sex1 ~1 0.474 0.006 76.503 0.000 0.462 0.486
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 sex.gcse ~1 -0.026 0.009 -3.018 0.003 -0.043 -0.009
## 15 Zalc r2 Zalc 0.014 NA NA NA NA NA
PE.modela2.alc$est[PE.modela2.alc$op == "r2"]
## [1] 0.01404955
(PE.modelb1.alc <- parameterEstimates(modelb1.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ SESscore 0.119 0.022 5.442 0.000 0.076 0.161
## 2 Zalc ~ Zgcse -0.020 0.021 -0.948 0.343 -0.062 0.022
## 3 Zalc ~~ Zalc 0.989 0.025 39.800 0.000 0.941 1.038
## 4 SESscore ~~ SESscore 0.875 0.016 56.316 0.000 0.844 0.905
## 5 SESscore ~~ Zgcse 0.447 0.013 34.430 0.000 0.422 0.473
## 6 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 7 Zalc ~1 -0.004 0.018 -0.200 0.841 -0.039 0.032
## 8 SESscore ~1 -0.034 0.012 -2.909 0.004 -0.057 -0.011
## 9 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 10 Zalc r2 Zalc 0.011 NA NA NA NA NA
PE.modelb1.alc$est[PE.modelb1.alc$op == "r2"]
## [1] 0.01058165
(PE.modelb2.alc <- parameterEstimates(modelb2.alcfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 Zalc ~ SESscore 0.118 0.022 5.289 0.000 0.075 0.162
## 2 Zalc ~ Zgcse -0.020 0.021 -0.946 0.344 -0.062 0.022
## 3 Zalc ~ SES.gcse 0.001 0.021 0.051 0.959 -0.039 0.041
## 4 Zalc ~~ Zalc 0.989 0.025 39.800 0.000 0.941 1.038
## 5 SESscore ~~ SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## 6 SESscore ~~ Zgcse 0.447 0.013 34.431 0.000 0.422 0.473
## 7 SESscore ~~ SES.gcse -0.013 0.011 -1.119 0.263 -0.035 0.010
## 8 Zgcse ~~ Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## 9 Zgcse ~~ SES.gcse -0.118 0.012 -9.663 0.000 -0.142 -0.094
## 10 SES.gcse ~~ SES.gcse 0.925 0.016 56.379 0.000 0.893 0.957
## 11 Zalc ~1 -0.004 0.020 -0.203 0.839 -0.043 0.035
## 12 SESscore ~1 -0.034 0.012 -2.909 0.004 -0.057 -0.011
## 13 Zgcse ~1 0.000 0.012 0.000 1.000 -0.024 0.024
## 14 SES.gcse ~1 0.444 0.012 36.803 0.000 0.420 0.467
## 15 Zalc r2 Zalc 0.011 NA NA NA NA NA
PE.modelb2.alc$est[PE.modelb2.alc$op == "r2"]
## [1] 0.01053766
r2diffa.alc <- (PE.modela2.alc$est[PE.modela2.alc$op == "r2"] - PE.modela1.alc$est[PE.modela1.alc$op == "r2"])
print(r2diffa.alc) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] -9.687592e-06
r2diffb.alc <- (PE.modelb2.alc$est[PE.modelb2.alc$op == "r2"] - PE.modelb1.alc$est[PE.modelb1.alc$op == "r2"])
print(r2diffb.alc) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] -4.398784e-05
logistic and multi-nominal regression with moderation
modela1.benf <- 'u1cbenf11 ~ sex1 + Zgcse'
modela1.benffit <- sem(modela1.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(modela1.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3736 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.186 0.077 -2.408 0.016 -0.338 -0.035
## Zgcse -0.294 0.037 -7.972 0.000 -0.367 -0.222
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.618 0.045 36.174 0.000 1.530 1.706
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.080
standardizedsolution(modela1.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.087 0.036 -2.427 0.015 -0.157 -0.017
## 2 u1cbenf11 ~ Zgcse -0.268 0.031 -8.587 0.000 -0.329 -0.207
## 3 u1cbenf11 | t1 1.552 0.046 33.437 0.000 1.461 1.643
## 4 u1cbenf11 ~~ u1cbenf11 0.920 0.018 52.144 0.000 0.886 0.955
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 9 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.788 0.000 NA NA 0.788 0.788
## 11 Zgcse ~1 0.206 0.000 NA NA 0.206 0.206
modela2.benf <- 'u1cbenf11 ~ sex1 + Zgcse + sex.gcse'
modela2.benffit <- sem(modela2.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(modela2.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 15 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3736 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.176 0.079 -2.235 0.025 -0.330 -0.022
## Zgcse -0.315 0.044 -7.225 0.000 -0.400 -0.229
## sex.gcse 0.061 0.083 0.742 0.458 -0.101 0.223
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.622 0.045 36.216 0.000 1.534 1.709
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.077
standardizedsolution(modela2.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.082 0.036 -2.252 0.024 -0.154 -0.011
## 2 u1cbenf11 ~ Zgcse -0.287 0.038 -7.560 0.000 -0.361 -0.212
## 3 u1cbenf11 ~ sex.gcse 0.036 0.048 0.740 0.459 -0.059 0.130
## 4 u1cbenf11 | t1 1.558 0.047 33.343 0.000 1.466 1.649
## 5 u1cbenf11 ~~ u1cbenf11 0.923 0.018 51.244 0.000 0.888 0.958
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ Zgcse 0.011 0.000 NA NA 0.011 0.011
## 8 sex1 ~~ sex.gcse 0.167 0.000 NA NA 0.167 0.167
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ sex.gcse 0.622 0.000 NA NA 0.622 0.622
## 11 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 13 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.788 0.000 NA NA 0.788 0.788
## 15 Zgcse ~1 0.206 0.000 NA NA 0.206 0.206
## 16 sex.gcse ~1 0.132 0.000 NA NA 0.132 0.132
modelb1.benf <- 'u1cbenf11 ~ SESscore + Zgcse'
modelb1.benffit <- sem(modelb1.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(modelb1.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3691 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## SESscore -0.140 0.043 -3.251 0.001 -0.224 -0.056
## Zgcse -0.232 0.041 -5.664 0.000 -0.312 -0.152
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.696 0.038 44.919 0.000 1.622 1.770
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.084
standardizedsolution(modelb1.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ SESscore -0.125 0.038 -3.297 0.001 -0.199 -0.051
## 2 u1cbenf11 ~ Zgcse -0.209 0.036 -5.868 0.000 -0.279 -0.139
## 3 u1cbenf11 | t1 1.623 0.036 44.801 0.000 1.552 1.694
## 4 u1cbenf11 ~~ u1cbenf11 0.916 0.018 49.897 0.000 0.880 0.952
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.466 0.000 NA NA 0.466 0.466
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 9 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.060 0.000 NA NA 0.060 0.060
## 11 Zgcse ~1 0.212 0.000 NA NA 0.212 0.212
modelb2.benf <- 'u1cbenf11 ~ SESscore + Zgcse + SES.gcse'
modelb2.benffit <- sem(modelb2.benf, data = df, ordered = c("u1cbenf11"), missing = "listwise")
summary(modelb2.benffit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 9 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3691 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## SESscore -0.139 0.043 -3.196 0.001 -0.224 -0.054
## Zgcse -0.227 0.043 -5.236 0.000 -0.312 -0.142
## SES.gcse 0.015 0.039 0.384 0.701 -0.062 0.092
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.701 0.040 42.728 0.000 1.623 1.779
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.081
standardizedsolution(modelb2.benffit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ SESscore -0.124 0.038 -3.246 0.001 -0.199 -0.049
## 2 u1cbenf11 ~ Zgcse -0.206 0.038 -5.448 0.000 -0.280 -0.132
## 3 u1cbenf11 ~ SES.gcse 0.013 0.034 0.383 0.702 -0.054 0.080
## 4 u1cbenf11 | t1 1.631 0.042 39.204 0.000 1.550 1.713
## 5 u1cbenf11 ~~ u1cbenf11 0.919 0.020 44.984 0.000 0.879 0.959
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 SESscore ~~ Zgcse 0.466 0.000 NA NA 0.466 0.466
## 8 SESscore ~~ SES.gcse 0.173 0.000 NA NA 0.173 0.173
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ SES.gcse 0.038 0.000 NA NA 0.038 0.038
## 11 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 13 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.060 0.000 NA NA 0.060 0.060
## 15 Zgcse ~1 0.212 0.000 NA NA 0.212 0.212
## 16 SES.gcse ~1 0.462 0.000 NA NA 0.462 0.462
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.benf <- parameterEstimates(modela1.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.186 0.077 -2.408 0.016 -0.338 -0.035
## 2 u1cbenf11 ~ Zgcse -0.294 0.037 -7.972 0.000 -0.367 -0.222
## 3 u1cbenf11 | t1 1.618 0.045 36.174 0.000 1.530 1.706
## 4 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.236 0.000 NA NA 0.236 0.236
## 6 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 7 Zgcse ~~ Zgcse 0.898 0.000 NA NA 0.898 0.898
## 8 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 9 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.383 0.000 NA NA 0.383 0.383
## 11 Zgcse ~1 0.195 0.000 NA NA 0.195 0.195
## 12 u1cbenf11 r2 u1cbenf11 0.080 NA NA NA NA NA
PE.modela1.benf$est[PE.modela1.benf$op == "r2"]
## [1] 0.07966791
(PE.modela2.benf <- parameterEstimates(modela2.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ sex1 -0.176 0.079 -2.235 0.025 -0.330 -0.022
## 2 u1cbenf11 ~ Zgcse -0.315 0.044 -7.225 0.000 -0.400 -0.229
## 3 u1cbenf11 ~ sex.gcse 0.061 0.083 0.742 0.458 -0.101 0.223
## 4 u1cbenf11 | t1 1.622 0.045 36.216 0.000 1.534 1.709
## 5 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.236 0.000 NA NA 0.236 0.236
## 7 sex1 ~~ Zgcse 0.005 0.000 NA NA 0.005 0.005
## 8 sex1 ~~ sex.gcse 0.049 0.000 NA NA 0.049 0.049
## 9 Zgcse ~~ Zgcse 0.898 0.000 NA NA 0.898 0.898
## 10 Zgcse ~~ sex.gcse 0.357 0.000 NA NA 0.357 0.357
## 11 sex.gcse ~~ sex.gcse 0.366 0.000 NA NA 0.366 0.366
## 12 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 13 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.383 0.000 NA NA 0.383 0.383
## 15 Zgcse ~1 0.195 0.000 NA NA 0.195 0.195
## 16 sex.gcse ~1 0.080 0.000 NA NA 0.080 0.080
## 17 u1cbenf11 r2 u1cbenf11 0.077 NA NA NA NA NA
PE.modela2.benf$est[PE.modela2.benf$op == "r2"]
## [1] 0.07705216
(PE.modelb1.benf <- parameterEstimates(modelb1.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ SESscore -0.140 0.043 -3.251 0.001 -0.224 -0.056
## 2 u1cbenf11 ~ Zgcse -0.232 0.041 -5.664 0.000 -0.312 -0.152
## 3 u1cbenf11 | t1 1.696 0.038 44.919 0.000 1.622 1.770
## 4 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ SESscore 0.871 0.000 NA NA 0.871 0.871
## 6 SESscore ~~ Zgcse 0.410 0.000 NA NA 0.410 0.410
## 7 Zgcse ~~ Zgcse 0.891 0.000 NA NA 0.891 0.891
## 8 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 9 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.056 0.000 NA NA 0.056 0.056
## 11 Zgcse ~1 0.201 0.000 NA NA 0.201 0.201
## 12 u1cbenf11 r2 u1cbenf11 0.084 NA NA NA NA NA
PE.modelb1.benf$est[PE.modelb1.benf$op == "r2"]
## [1] 0.08387213
(PE.modelb2.benf <- parameterEstimates(modelb2.benffit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 u1cbenf11 ~ SESscore -0.139 0.043 -3.196 0.001 -0.224 -0.054
## 2 u1cbenf11 ~ Zgcse -0.227 0.043 -5.236 0.000 -0.312 -0.142
## 3 u1cbenf11 ~ SES.gcse 0.015 0.039 0.384 0.701 -0.062 0.092
## 4 u1cbenf11 | t1 1.701 0.040 42.728 0.000 1.623 1.779
## 5 u1cbenf11 ~~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ SESscore 0.871 0.000 NA NA 0.871 0.871
## 7 SESscore ~~ Zgcse 0.410 0.000 NA NA 0.410 0.410
## 8 SESscore ~~ SES.gcse 0.147 0.000 NA NA 0.147 0.147
## 9 Zgcse ~~ Zgcse 0.891 0.000 NA NA 0.891 0.891
## 10 Zgcse ~~ SES.gcse 0.033 0.000 NA NA 0.033 0.033
## 11 SES.gcse ~~ SES.gcse 0.834 0.000 NA NA 0.834 0.834
## 12 u1cbenf11 ~*~ u1cbenf11 1.000 0.000 NA NA 1.000 1.000
## 13 u1cbenf11 ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.056 0.000 NA NA 0.056 0.056
## 15 Zgcse ~1 0.201 0.000 NA NA 0.201 0.201
## 16 SES.gcse ~1 0.422 0.000 NA NA 0.422 0.422
## 17 u1cbenf11 r2 u1cbenf11 0.081 NA NA NA NA NA
PE.modelb2.benf$est[PE.modelb2.benf$op == "r2"]
## [1] 0.08077858
r2diffa.benf <- (PE.modela2.benf$est[PE.modela2.benf$op == "r2"] - PE.modela1.benf$est[PE.modela1.benf$op == "r2"])
print(r2diffa.benf) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] -0.002615749
r2diffb.benf <- (PE.modelb2.benf$est[PE.modelb2.benf$op == "r2"] - PE.modelb1.benf$est[PE.modelb1.benf$op == "r2"])
print(r2diffb.benf) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] -0.003093544
modela1.status_bin <- 'status_bin ~ sex1 + Zgcse'
modela1.status_binfit <- sem(modela1.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(modela1.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.028 0.057 -0.490 0.624 -0.139 0.083
## Zgcse -0.016 0.028 -0.595 0.552 -0.071 0.038
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.277 0.036 -35.627 0.000 -1.347 -1.206
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.000
standardizedsolution(modela1.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.014 0.028 -0.490 0.624 -0.068 0.041
## 2 status_bin ~ Zgcse -0.016 0.026 -0.595 0.552 -0.067 0.036
## 3 status_bin | t1 -1.276 0.035 -35.997 0.000 -1.346 -1.207
## 4 status_bin ~~ status_bin 1.000 0.001 907.238 0.000 0.997 1.002
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 9 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
modela2.status_bin <- 'status_bin ~ sex1 + Zgcse + sex.gcse'
modela2.status_binfit <- sem(modela2.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(modela2.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 13 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.023 0.058 -0.401 0.688 -0.137 0.091
## Zgcse -0.008 0.035 -0.232 0.816 -0.078 0.061
## sex.gcse -0.021 0.057 -0.363 0.716 -0.131 0.090
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.275 0.036 -35.306 0.000 -1.346 -1.204
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.001
standardizedsolution(modela2.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.011 0.028 -0.401 0.688 -0.067 0.044
## 2 status_bin ~ Zgcse -0.008 0.033 -0.232 0.816 -0.073 0.058
## 3 status_bin ~ sex.gcse -0.012 0.034 -0.363 0.716 -0.080 0.055
## 4 status_bin | t1 -1.275 0.036 -35.626 0.000 -1.345 -1.205
## 5 status_bin ~~ status_bin 0.999 0.001 830.245 0.000 0.997 1.002
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 8 sex1 ~~ sex.gcse 0.171 0.000 NA NA 0.171 0.171
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ sex.gcse 0.624 0.000 NA NA 0.624 0.624
## 11 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 13 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
## 16 sex.gcse ~1 0.135 0.000 NA NA 0.135 0.135
modelb1.status_bin <- 'status_bin ~ SESscore + Zgcse'
modelb1.status_binfit <- sem(modelb1.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(modelb1.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 4 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## SESscore -0.065 0.034 -1.893 0.058 -0.132 0.002
## Zgcse 0.011 0.033 0.320 0.749 -0.054 0.076
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.268 0.029 -44.377 0.000 -1.324 -1.212
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.003
standardizedsolution(modelb1.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ SESscore -0.060 0.032 -1.898 0.058 -0.123 0.002
## 2 status_bin ~ Zgcse 0.010 0.031 0.320 0.749 -0.051 0.071
## 3 status_bin | t1 -1.266 0.028 -44.459 0.000 -1.322 -1.210
## 4 status_bin ~~ status_bin 0.997 0.003 321.026 0.000 0.991 1.003
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 9 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 11 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
modelb2.status_bin <- 'status_bin ~ SESscore + Zgcse + SES.gcse'
modelb2.status_binfit <- sem(modelb2.status_bin, data = df, ordered = c("status_bin"), missing = "listwise")
summary(modelb2.status_binfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 9 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## SESscore -0.053 0.034 -1.547 0.122 -0.121 0.014
## Zgcse 0.009 0.033 0.261 0.794 -0.056 0.074
## SES.gcse -0.062 0.030 -2.079 0.038 -0.120 -0.004
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.296 0.032 -40.572 0.000 -1.358 -1.233
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.006
standardizedsolution(modelb2.status_binfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 status_bin ~ SESscore -0.050 0.032 -1.550 0.121 -0.112 0.013
## 2 status_bin ~ Zgcse 0.008 0.031 0.261 0.794 -0.053 0.069
## 3 status_bin ~ SES.gcse -0.056 0.027 -2.086 0.037 -0.109 -0.003
## 4 status_bin | t1 -1.292 0.031 -41.716 0.000 -1.352 -1.231
## 5 status_bin ~~ status_bin 0.994 0.004 229.405 0.000 0.985 1.002
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 8 SESscore ~~ SES.gcse 0.175 0.000 NA NA 0.175 0.175
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ SES.gcse 0.037 0.000 NA NA 0.037 0.037
## 11 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 13 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 15 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
## 16 SES.gcse ~1 0.463 0.000 NA NA 0.463 0.463
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.status_bin <- parameterEstimates(modela1.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.028 0.057 -0.490 0.624 -0.139 0.083
## 2 status_bin ~ Zgcse -0.016 0.028 -0.595 0.552 -0.071 0.038
## 3 status_bin | t1 -1.277 0.036 -35.627 0.000 -1.347 -1.206
## 4 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 7 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 8 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 9 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 12 status_bin r2 status_bin 0.000 NA NA NA NA NA
PE.modela1.status_bin$est[PE.modela1.status_bin$op == "r2"]
## [1] 0.0004300602
(PE.modela2.status_bin <- parameterEstimates(modela2.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ sex1 -0.023 0.058 -0.401 0.688 -0.137 0.091
## 2 status_bin ~ Zgcse -0.008 0.035 -0.232 0.816 -0.078 0.061
## 3 status_bin ~ sex.gcse -0.021 0.057 -0.363 0.716 -0.131 0.090
## 4 status_bin | t1 -1.275 0.036 -35.306 0.000 -1.346 -1.204
## 5 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 8 sex1 ~~ sex.gcse 0.050 0.000 NA NA 0.050 0.050
## 9 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 10 Zgcse ~~ sex.gcse 0.357 0.000 NA NA 0.357 0.357
## 11 sex.gcse ~~ sex.gcse 0.366 0.000 NA NA 0.366 0.366
## 12 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 13 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 16 sex.gcse ~1 0.082 0.000 NA NA 0.082 0.082
## 17 status_bin r2 status_bin 0.001 NA NA NA NA NA
PE.modela2.status_bin$est[PE.modela2.status_bin$op == "r2"]
## [1] 0.0005144954
(PE.modelb1.status_bin <- parameterEstimates(modelb1.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ SESscore -0.065 0.034 -1.893 0.058 -0.132 0.002
## 2 status_bin ~ Zgcse 0.011 0.033 0.320 0.749 -0.054 0.076
## 3 status_bin | t1 -1.268 0.029 -44.377 0.000 -1.324 -1.212
## 4 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 6 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 7 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 8 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 9 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 11 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 12 status_bin r2 status_bin 0.003 NA NA NA NA NA
PE.modelb1.status_bin$est[PE.modelb1.status_bin$op == "r2"]
## [1] 0.003179829
(PE.modelb2.status_bin <- parameterEstimates(modelb2.status_binfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 status_bin ~ SESscore -0.053 0.034 -1.547 0.122 -0.121 0.014
## 2 status_bin ~ Zgcse 0.009 0.033 0.261 0.794 -0.056 0.074
## 3 status_bin ~ SES.gcse -0.062 0.030 -2.079 0.038 -0.120 -0.004
## 4 status_bin | t1 -1.296 0.032 -40.572 0.000 -1.358 -1.233
## 5 status_bin ~~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 7 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 8 SESscore ~~ SES.gcse 0.149 0.000 NA NA 0.149 0.149
## 9 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 10 Zgcse ~~ SES.gcse 0.032 0.000 NA NA 0.032 0.032
## 11 SES.gcse ~~ SES.gcse 0.833 0.000 NA NA 0.833 0.833
## 12 status_bin ~*~ status_bin 1.000 0.000 NA NA 1.000 1.000
## 13 status_bin ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 15 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 16 SES.gcse ~1 0.422 0.000 NA NA 0.422 0.422
## 17 status_bin r2 status_bin 0.006 NA NA NA NA NA
PE.modelb2.status_bin$est[PE.modelb2.status_bin$op == "r2"]
## [1] 0.006225163
r2diffa.status_bin <- (PE.modela2.status_bin$est[PE.modela2.status_bin$op == "r2"] - PE.modela1.status_bin$est[PE.modela1.status_bin$op == "r2"])
print(r2diffa.status_bin) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 8.443518e-05
r2diffb.status_bin <- (PE.modelb2.status_bin$est[PE.modelb2.status_bin$op == "r2"] - PE.modelb1.status_bin$est[PE.modelb1.status_bin$op == "r2"])
print(r2diffb.status_bin) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.003045334
“Multinomial”/logistic regression with moderation for each category of employment status (dummy variables)
#create interaction term also in df-dummy dataset that contains the dummy variables for employment status
df_dummy$sex.gcse <- df_dummy$sex1*df$Zgcse
df_dummy$SES.gcse <- df_dummy$SESscore*df$Zgcse
##employment status: working vs. unemployed
modela1.st_working <- 'st_working ~ sex1 + Zgcse'
modela1.st_workingfit <- sem(modela1.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(modela1.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 8 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.131 0.043 -3.058 0.002 -0.215 -0.047
## Zgcse -0.356 0.021 -16.717 0.000 -0.398 -0.315
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.158 0.027 -5.849 0.000 -0.211 -0.105
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.106
standardizedsolution(modela1.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.060 0.020 -3.069 0.002 -0.099 -0.022
## 2 st_working ~ Zgcse -0.318 0.017 -18.600 0.000 -0.352 -0.285
## 3 st_working | t1 -0.149 0.025 -5.900 0.000 -0.199 -0.100
## 4 st_working ~~ st_working 0.894 0.011 80.605 0.000 0.873 0.916
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 9 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
modela2.st_working <- 'st_working ~ sex1 + Zgcse + sex.gcse'
modela2.st_workingfit <- sem(modela2.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(modela2.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.143 0.044 -3.270 0.001 -0.229 -0.057
## Zgcse -0.378 0.027 -13.770 0.000 -0.432 -0.324
## sex.gcse 0.054 0.044 1.249 0.212 -0.031 0.140
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.163 0.027 -6.001 0.000 -0.216 -0.110
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.106
standardizedsolution(modela2.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.066 0.020 -3.283 0.001 -0.105 -0.027
## 2 st_working ~ Zgcse -0.338 0.023 -14.761 0.000 -0.383 -0.293
## 3 st_working ~ sex.gcse 0.031 0.025 1.249 0.212 -0.018 0.080
## 4 st_working | t1 -0.154 0.025 -6.056 0.000 -0.204 -0.104
## 5 st_working ~~ st_working 0.894 0.011 80.435 0.000 0.872 0.916
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 8 sex1 ~~ sex.gcse 0.171 0.000 NA NA 0.171 0.171
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ sex.gcse 0.624 0.000 NA NA 0.624 0.624
## 11 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 13 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
## 16 sex.gcse ~1 0.135 0.000 NA NA 0.135 0.135
modelb1.st_working <- 'st_working ~ SESscore + Zgcse'
modelb1.st_workingfit <- sem(modelb1.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(modelb1.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 5 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## SESscore -0.183 0.025 -7.204 0.000 -0.233 -0.133
## Zgcse -0.277 0.025 -11.255 0.000 -0.325 -0.228
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.105 0.022 -4.859 0.000 -0.147 -0.063
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.122
standardizedsolution(modelb1.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ SESscore -0.160 0.022 -7.353 0 -0.203 -0.118
## 2 st_working ~ Zgcse -0.244 0.021 -11.782 0 -0.285 -0.204
## 3 st_working | t1 -0.098 0.020 -4.882 0 -0.138 -0.059
## 4 st_working ~~ st_working 0.878 0.012 73.184 0 0.855 0.902
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 9 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 11 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
modelb2.st_working <- 'st_working ~ SESscore + Zgcse + SES.gcse'
modelb2.st_workingfit <- sem(modelb2.st_working, data = df_dummy, ordered = c("st_working"), missing = "listwise")
summary(modelb2.st_workingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## SESscore -0.176 0.026 -6.860 0.000 -0.226 -0.126
## Zgcse -0.278 0.025 -11.203 0.000 -0.326 -0.229
## SES.gcse -0.034 0.023 -1.497 0.134 -0.078 0.010
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.118 0.024 -4.978 0.000 -0.164 -0.071
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.122
standardizedsolution(modelb2.st_workingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_working ~ SESscore -0.154 0.022 -6.986 0.000 -0.198 -0.111
## 2 st_working ~ Zgcse -0.245 0.021 -11.742 0.000 -0.286 -0.204
## 3 st_working ~ SES.gcse -0.029 0.019 -1.499 0.134 -0.067 0.009
## 4 st_working | t1 -0.110 0.022 -5.011 0.000 -0.153 -0.067
## 5 st_working ~~ st_working 0.878 0.012 72.102 0.000 0.854 0.902
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 8 SESscore ~~ SES.gcse 0.175 0.000 NA NA 0.175 0.175
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ SES.gcse 0.037 0.000 NA NA 0.037 0.037
## 11 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 13 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 15 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
## 16 SES.gcse ~1 0.463 0.000 NA NA 0.463 0.463
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.st_working <- parameterEstimates(modela1.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.131 0.043 -3.058 0.002 -0.215 -0.047
## 2 st_working ~ Zgcse -0.356 0.021 -16.717 0.000 -0.398 -0.315
## 3 st_working | t1 -0.158 0.027 -5.849 0.000 -0.211 -0.105
## 4 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 7 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 8 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 9 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 12 st_working r2 st_working 0.106 NA NA NA NA NA
PE.modela1.st_working$est[PE.modela1.st_working$op == "r2"]
## [1] 0.1055824
(PE.modela2.st_working <- parameterEstimates(modela2.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ sex1 -0.143 0.044 -3.270 0.001 -0.229 -0.057
## 2 st_working ~ Zgcse -0.378 0.027 -13.770 0.000 -0.432 -0.324
## 3 st_working ~ sex.gcse 0.054 0.044 1.249 0.212 -0.031 0.140
## 4 st_working | t1 -0.163 0.027 -6.001 0.000 -0.216 -0.110
## 5 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 8 sex1 ~~ sex.gcse 0.050 0.000 NA NA 0.050 0.050
## 9 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 10 Zgcse ~~ sex.gcse 0.357 0.000 NA NA 0.357 0.357
## 11 sex.gcse ~~ sex.gcse 0.366 0.000 NA NA 0.366 0.366
## 12 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 13 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 16 sex.gcse ~1 0.082 0.000 NA NA 0.082 0.082
## 17 st_working r2 st_working 0.106 NA NA NA NA NA
PE.modela2.st_working$est[PE.modela2.st_working$op == "r2"]
## [1] 0.1062769
(PE.modelb1.st_working <- parameterEstimates(modelb1.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ SESscore -0.183 0.025 -7.204 0 -0.233 -0.133
## 2 st_working ~ Zgcse -0.277 0.025 -11.255 0 -0.325 -0.228
## 3 st_working | t1 -0.105 0.022 -4.859 0 -0.147 -0.063
## 4 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 6 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 7 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 8 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 9 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 11 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 12 st_working r2 st_working 0.122 NA NA NA NA NA
PE.modelb1.st_working$est[PE.modelb1.st_working$op == "r2"]
## [1] 0.1219176
(PE.modelb2.st_working <- parameterEstimates(modelb2.st_workingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_working ~ SESscore -0.176 0.026 -6.860 0.000 -0.226 -0.126
## 2 st_working ~ Zgcse -0.278 0.025 -11.203 0.000 -0.326 -0.229
## 3 st_working ~ SES.gcse -0.034 0.023 -1.497 0.134 -0.078 0.010
## 4 st_working | t1 -0.118 0.024 -4.978 0.000 -0.164 -0.071
## 5 st_working ~~ st_working 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 7 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 8 SESscore ~~ SES.gcse 0.149 0.000 NA NA 0.149 0.149
## 9 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 10 Zgcse ~~ SES.gcse 0.032 0.000 NA NA 0.032 0.032
## 11 SES.gcse ~~ SES.gcse 0.833 0.000 NA NA 0.833 0.833
## 12 st_working ~*~ st_working 1.000 0.000 NA NA 1.000 1.000
## 13 st_working ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 15 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 16 SES.gcse ~1 0.422 0.000 NA NA 0.422 0.422
## 17 st_working r2 st_working 0.122 NA NA NA NA NA
PE.modelb2.st_working$est[PE.modelb2.st_working$op == "r2"]
## [1] 0.1221907
r2diffa.st_working <- (PE.modela2.st_working$est[PE.modela2.st_working$op == "r2"] - PE.modela1.st_working$est[PE.modela1.st_working$op == "r2"])
print(r2diffa.st_working) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.000694489
r2diffb.st_working <- (PE.modelb2.st_working$est[PE.modelb2.st_working$op == "r2"] - PE.modelb1.st_working$est[PE.modelb1.st_working$op == "r2"])
print(r2diffb.st_working) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.0002730553
##employment status: studying/apprenticeship vs. unemployed
modela1.st_studying <- 'st_studying ~ sex1 + Zgcse'
modela1.st_studyingfit <- sem(modela1.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(modela1.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.124 0.044 2.851 0.004 0.039 0.210
## Zgcse 0.376 0.023 16.472 0.000 0.331 0.420
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.441 0.028 15.646 0.000 0.385 0.496
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.115
standardizedsolution(modela1.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.057 0.020 2.861 0.004 0.018 0.096
## 2 st_studying ~ Zgcse 0.334 0.018 18.542 0.000 0.299 0.369
## 3 st_studying | t1 0.414 0.026 16.130 0.000 0.364 0.465
## 4 st_studying ~~ st_studying 0.885 0.012 72.442 0.000 0.861 0.909
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 9 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
modela2.st_studying <- 'st_studying ~ sex1 + Zgcse + sex.gcse'
modela2.st_studyingfit <- sem(modela2.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(modela2.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 12 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.148 0.045 3.256 0.001 0.059 0.237
## Zgcse 0.410 0.029 13.901 0.000 0.352 0.468
## sex.gcse -0.083 0.047 -1.793 0.073 -0.175 0.008
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.450 0.028 15.809 0.000 0.395 0.506
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.117
standardizedsolution(modela2.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.068 0.021 3.271 0.001 0.027 0.108
## 2 st_studying ~ Zgcse 0.364 0.024 15.097 0.000 0.317 0.411
## 3 st_studying ~ sex.gcse -0.047 0.026 -1.796 0.073 -0.099 0.004
## 4 st_studying | t1 0.423 0.026 16.331 0.000 0.372 0.474
## 5 st_studying ~~ st_studying 0.883 0.012 71.789 0.000 0.859 0.907
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 8 sex1 ~~ sex.gcse 0.171 0.000 NA NA 0.171 0.171
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ sex.gcse 0.624 0.000 NA NA 0.624 0.624
## 11 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 13 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
## 16 sex.gcse ~1 0.135 0.000 NA NA 0.135 0.135
modelb1.st_studying <- 'st_studying ~ SESscore + Zgcse'
modelb1.st_studyingfit <- sem(modelb1.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(modelb1.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 4 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## SESscore 0.159 0.026 6.216 0.000 0.109 0.209
## Zgcse 0.303 0.026 11.834 0.000 0.253 0.353
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.391 0.022 17.417 0.000 0.347 0.435
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.125
standardizedsolution(modelb1.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ SESscore 0.139 0.022 6.315 0 0.096 0.182
## 2 st_studying ~ Zgcse 0.267 0.021 12.540 0 0.225 0.309
## 3 st_studying | t1 0.366 0.020 17.885 0 0.326 0.406
## 4 st_studying ~~ st_studying 0.875 0.013 68.878 0 0.850 0.899
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 9 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 11 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
modelb2.st_studying <- 'st_studying ~ SESscore + Zgcse + SES.gcse'
modelb2.st_studyingfit <- sem(modelb2.st_studying, data = df_dummy, ordered = c("st_studying"), missing = "listwise")
summary(modelb2.st_studyingfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## SESscore 0.166 0.026 6.307 0.000 0.114 0.218
## Zgcse 0.304 0.026 11.878 0.000 0.254 0.354
## SES.gcse -0.026 0.024 -1.094 0.274 -0.072 0.020
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.382 0.024 15.661 0.000 0.334 0.430
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.128
standardizedsolution(modelb2.st_studyingfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_studying ~ SESscore 0.145 0.023 6.411 0.000 0.101 0.189
## 2 st_studying ~ Zgcse 0.267 0.021 12.573 0.000 0.226 0.309
## 3 st_studying ~ SES.gcse -0.022 0.020 -1.095 0.274 -0.061 0.017
## 4 st_studying | t1 0.357 0.022 15.938 0.000 0.313 0.401
## 5 st_studying ~~ st_studying 0.872 0.013 68.764 0.000 0.847 0.897
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 8 SESscore ~~ SES.gcse 0.175 0.000 NA NA 0.175 0.175
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ SES.gcse 0.037 0.000 NA NA 0.037 0.037
## 11 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 13 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 15 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
## 16 SES.gcse ~1 0.463 0.000 NA NA 0.463 0.463
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.st_studying <- parameterEstimates(modela1.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.124 0.044 2.851 0.004 0.039 0.210
## 2 st_studying ~ Zgcse 0.376 0.023 16.472 0.000 0.331 0.420
## 3 st_studying | t1 0.441 0.028 15.646 0.000 0.385 0.496
## 4 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 7 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 8 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 9 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 12 st_studying r2 st_studying 0.115 NA NA NA NA NA
PE.modela1.st_studying$est[PE.modela1.st_studying$op == "r2"]
## [1] 0.1152685
(PE.modela2.st_studying <- parameterEstimates(modela2.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ sex1 0.148 0.045 3.256 0.001 0.059 0.237
## 2 st_studying ~ Zgcse 0.410 0.029 13.901 0.000 0.352 0.468
## 3 st_studying ~ sex.gcse -0.083 0.047 -1.793 0.073 -0.175 0.008
## 4 st_studying | t1 0.450 0.028 15.809 0.000 0.395 0.506
## 5 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 8 sex1 ~~ sex.gcse 0.050 0.000 NA NA 0.050 0.050
## 9 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 10 Zgcse ~~ sex.gcse 0.357 0.000 NA NA 0.357 0.357
## 11 sex.gcse ~~ sex.gcse 0.366 0.000 NA NA 0.366 0.366
## 12 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 13 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 16 sex.gcse ~1 0.082 0.000 NA NA 0.082 0.082
## 17 st_studying r2 st_studying 0.117 NA NA NA NA NA
PE.modela2.st_studying$est[PE.modela2.st_studying$op == "r2"]
## [1] 0.1173589
(PE.modelb1.st_studying <- parameterEstimates(modelb1.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ SESscore 0.159 0.026 6.216 0 0.109 0.209
## 2 st_studying ~ Zgcse 0.303 0.026 11.834 0 0.253 0.353
## 3 st_studying | t1 0.391 0.022 17.417 0 0.347 0.435
## 4 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 6 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 7 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 8 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 9 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 11 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 12 st_studying r2 st_studying 0.125 NA NA NA NA NA
PE.modelb1.st_studying$est[PE.modelb1.st_studying$op == "r2"]
## [1] 0.1253878
(PE.modelb2.st_studying <- parameterEstimates(modelb2.st_studyingfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_studying ~ SESscore 0.166 0.026 6.307 0.000 0.114 0.218
## 2 st_studying ~ Zgcse 0.304 0.026 11.878 0.000 0.254 0.354
## 3 st_studying ~ SES.gcse -0.026 0.024 -1.094 0.274 -0.072 0.020
## 4 st_studying | t1 0.382 0.024 15.661 0.000 0.334 0.430
## 5 st_studying ~~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 7 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 8 SESscore ~~ SES.gcse 0.149 0.000 NA NA 0.149 0.149
## 9 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 10 Zgcse ~~ SES.gcse 0.032 0.000 NA NA 0.032 0.032
## 11 SES.gcse ~~ SES.gcse 0.833 0.000 NA NA 0.833 0.833
## 12 st_studying ~*~ st_studying 1.000 0.000 NA NA 1.000 1.000
## 13 st_studying ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 15 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 16 SES.gcse ~1 0.422 0.000 NA NA 0.422 0.422
## 17 st_studying r2 st_studying 0.128 NA NA NA NA NA
PE.modelb2.st_studying$est[PE.modelb2.st_studying$op == "r2"]
## [1] 0.1276366
r2diffa.st_studying <- (PE.modela2.st_studying$est[PE.modela2.st_studying$op == "r2"] - PE.modela1.st_studying$est[PE.modela1.st_studying$op == "r2"])
print(r2diffa.st_studying) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.002090444
r2diffb.st_studying <- (PE.modelb2.st_studying$est[PE.modelb2.st_studying$op == "r2"] - PE.modelb1.st_studying$est[PE.modelb1.st_studying$op == "r2"])
print(r2diffb.st_studying) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] 0.002248734
##employment status: full-time parent vs. unemployed
modela1.st_parent <- 'st_parent ~ sex1 + Zgcse'
modela1.st_parentfit <- sem(modela1.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(modela1.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 10 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.542 0.221 -2.453 0.014 -0.976 -0.109
## Zgcse -0.420 0.077 -5.450 0.000 -0.571 -0.269
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.497 0.100 25.066 0.000 2.302 2.692
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.187
standardizedsolution(modela1.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.238 0.091 -2.623 0.009 -0.416 -0.060
## 2 st_parent ~ Zgcse -0.358 0.057 -6.335 0.000 -0.469 -0.247
## 3 st_parent | t1 2.251 0.113 19.864 0.000 2.029 2.474
## 4 st_parent ~~ st_parent 0.813 0.058 13.934 0.000 0.699 0.927
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 9 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
modela2.st_parent <- 'st_parent ~ sex1 + Zgcse + sex.gcse'
modela2.st_parentfit <- sem(modela2.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(modela2.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 11 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.540 0.338 -1.599 0.110 -1.203 0.122
## Zgcse -0.421 0.081 -5.175 0.000 -0.580 -0.261
## sex.gcse 0.002 0.257 0.009 0.993 -0.501 0.506
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.497 0.101 24.778 0.000 2.300 2.695
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.186
standardizedsolution(modela2.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.237 0.134 -1.767 0.077 -0.500 0.026
## 2 st_parent ~ Zgcse -0.359 0.070 -5.090 0.000 -0.497 -0.221
## 3 st_parent ~ sex.gcse 0.001 0.140 0.009 0.993 -0.274 0.276
## 4 st_parent | t1 2.253 0.180 12.503 0.000 1.899 2.606
## 5 st_parent ~~ st_parent 0.814 0.108 7.517 0.000 0.602 1.026
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 8 sex1 ~~ sex.gcse 0.171 0.000 NA NA 0.171 0.171
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ sex.gcse 0.624 0.000 NA NA 0.624 0.624
## 11 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 13 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
## 16 sex.gcse ~1 0.135 0.000 NA NA 0.135 0.135
modelb1.st_parent <- 'st_parent ~ SESscore + Zgcse'
modelb1.st_parentfit <- sem(modelb1.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(modelb1.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 9 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## SESscore -0.349 0.109 -3.215 0.001 -0.563 -0.136
## Zgcse -0.301 0.086 -3.504 0.000 -0.469 -0.133
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.754 0.116 23.646 0.000 2.525 2.982
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.215
standardizedsolution(modelb1.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ SESscore -0.289 0.083 -3.497 0 -0.452 -0.127
## 2 st_parent ~ Zgcse -0.251 0.069 -3.655 0 -0.386 -0.116
## 3 st_parent | t1 2.440 0.075 32.676 0 2.294 2.587
## 4 st_parent ~~ st_parent 0.785 0.058 13.629 0 0.672 0.898
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 9 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 11 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
modelb2.st_parent <- 'st_parent ~ SESscore + Zgcse + SES.gcse'
modelb2.st_parentfit <- sem(modelb2.st_parent, data = df_dummy, ordered = c("st_parent"), missing = "listwise")
summary(modelb2.st_parentfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 18 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## SESscore -0.325 0.118 -2.745 0.006 -0.557 -0.093
## Zgcse -0.252 0.191 -1.317 0.188 -0.627 0.123
## SES.gcse 0.054 0.135 0.399 0.690 -0.211 0.318
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.746 0.123 22.328 0.000 2.505 2.987
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.175
standardizedsolution(modelb2.st_parentfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_parent ~ SESscore -0.276 0.088 -3.124 0.002 -0.449 -0.103
## 2 st_parent ~ Zgcse -0.215 0.150 -1.438 0.151 -0.509 0.078
## 3 st_parent ~ SES.gcse 0.045 0.115 0.389 0.697 -0.180 0.270
## 4 st_parent | t1 2.494 0.150 16.624 0.000 2.200 2.788
## 5 st_parent ~~ st_parent 0.825 0.123 6.717 0.000 0.584 1.066
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 8 SESscore ~~ SES.gcse 0.175 0.000 NA NA 0.175 0.175
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ SES.gcse 0.037 0.000 NA NA 0.037 0.037
## 11 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 13 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 15 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
## 16 SES.gcse ~1 0.463 0.000 NA NA 0.463 0.463
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.st_parent <- parameterEstimates(modela1.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.542 0.221 -2.453 0.014 -0.976 -0.109
## 2 st_parent ~ Zgcse -0.420 0.077 -5.450 0.000 -0.571 -0.269
## 3 st_parent | t1 2.497 0.100 25.066 0.000 2.302 2.692
## 4 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 7 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 8 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 9 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 12 st_parent r2 st_parent 0.187 NA NA NA NA NA
PE.modela1.st_parent$est[PE.modela1.st_parent$op == "r2"]
## [1] 0.1870129
(PE.modela2.st_parent <- parameterEstimates(modela2.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ sex1 -0.540 0.338 -1.599 0.110 -1.203 0.122
## 2 st_parent ~ Zgcse -0.421 0.081 -5.175 0.000 -0.580 -0.261
## 3 st_parent ~ sex.gcse 0.002 0.257 0.009 0.993 -0.501 0.506
## 4 st_parent | t1 2.497 0.101 24.778 0.000 2.300 2.695
## 5 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 8 sex1 ~~ sex.gcse 0.050 0.000 NA NA 0.050 0.050
## 9 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 10 Zgcse ~~ sex.gcse 0.357 0.000 NA NA 0.357 0.357
## 11 sex.gcse ~~ sex.gcse 0.366 0.000 NA NA 0.366 0.366
## 12 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 13 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 16 sex.gcse ~1 0.082 0.000 NA NA 0.082 0.082
## 17 st_parent r2 st_parent 0.186 NA NA NA NA NA
PE.modela2.st_parent$est[PE.modela2.st_parent$op == "r2"]
## [1] 0.1863282
(PE.modelb1.st_parent <- parameterEstimates(modelb1.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ SESscore -0.349 0.109 -3.215 0.001 -0.563 -0.136
## 2 st_parent ~ Zgcse -0.301 0.086 -3.504 0.000 -0.469 -0.133
## 3 st_parent | t1 2.754 0.116 23.646 0.000 2.525 2.982
## 4 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 6 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 7 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 8 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 9 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 11 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 12 st_parent r2 st_parent 0.215 NA NA NA NA NA
PE.modelb1.st_parent$est[PE.modelb1.st_parent$op == "r2"]
## [1] 0.2147373
(PE.modelb2.st_parent <- parameterEstimates(modelb2.st_parentfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_parent ~ SESscore -0.325 0.118 -2.745 0.006 -0.557 -0.093
## 2 st_parent ~ Zgcse -0.252 0.191 -1.317 0.188 -0.627 0.123
## 3 st_parent ~ SES.gcse 0.054 0.135 0.399 0.690 -0.211 0.318
## 4 st_parent | t1 2.746 0.123 22.328 0.000 2.505 2.987
## 5 st_parent ~~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 7 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 8 SESscore ~~ SES.gcse 0.149 0.000 NA NA 0.149 0.149
## 9 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 10 Zgcse ~~ SES.gcse 0.032 0.000 NA NA 0.032 0.032
## 11 SES.gcse ~~ SES.gcse 0.833 0.000 NA NA 0.833 0.833
## 12 st_parent ~*~ st_parent 1.000 0.000 NA NA 1.000 1.000
## 13 st_parent ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 15 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 16 SES.gcse ~1 0.422 0.000 NA NA 0.422 0.422
## 17 st_parent r2 st_parent 0.175 NA NA NA NA NA
PE.modelb2.st_parent$est[PE.modelb2.st_parent$op == "r2"]
## [1] 0.1750283
r2diffa.st_parent <- (PE.modela2.st_parent$est[PE.modela2.st_parent$op == "r2"] - PE.modela1.st_parent$est[PE.modela1.st_parent$op == "r2"])
print(r2diffa.st_parent) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] -0.0006847078
r2diffb.st_parent <- (PE.modelb2.st_parent$est[PE.modelb2.st_parent$op == "r2"] - PE.modelb1.st_parent$est[PE.modelb1.st_parent$op == "r2"])
print(r2diffb.st_parent) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] -0.03970895
##employment status: gap year/travelling vs. unemployed
modela1.st_gapyear <- 'st_gapyear ~ sex1 + Zgcse'
modela1.st_gapyearfit <- sem(modela1.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(modela1.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 8 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 -0.078 0.082 -0.951 0.342 -0.238 0.083
## Zgcse 0.121 0.044 2.770 0.006 0.035 0.206
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.819 0.052 34.720 0.000 1.716 1.921
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.014
standardizedsolution(modela1.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.038 0.040 -0.952 0.341 -0.115 0.040
## 2 st_gapyear ~ Zgcse 0.113 0.040 2.805 0.005 0.034 0.193
## 3 st_gapyear | t1 1.806 0.051 35.244 0.000 1.705 1.906
## 4 st_gapyear ~~ st_gapyear 0.986 0.009 106.962 0.000 0.968 1.004
## 5 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 9 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 11 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
modela2.st_gapyear <- 'st_gapyear ~ sex1 + Zgcse + sex.gcse'
modela2.st_gapyearfit <- sem(modela2.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(modela2.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 17 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3743 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 -0.030 0.087 -0.341 0.733 -0.199 0.140
## Zgcse 0.176 0.057 3.109 0.002 0.065 0.288
## sex.gcse -0.144 0.090 -1.609 0.108 -0.320 0.031
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.840 0.054 34.024 0.000 1.734 1.946
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.018
standardizedsolution(modela2.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.014 0.042 -0.341 0.733 -0.096 0.068
## 2 st_gapyear ~ Zgcse 0.165 0.052 3.159 0.002 0.063 0.268
## 3 st_gapyear ~ sex.gcse -0.086 0.054 -1.616 0.106 -0.191 0.018
## 4 st_gapyear | t1 1.824 0.051 35.419 0.000 1.723 1.924
## 5 st_gapyear ~~ st_gapyear 0.982 0.010 94.221 0.000 0.962 1.003
## 6 sex1 ~~ sex1 1.000 0.000 NA NA 1.000 1.000
## 7 sex1 ~~ Zgcse 0.013 0.000 NA NA 0.013 0.013
## 8 sex1 ~~ sex.gcse 0.171 0.000 NA NA 0.171 0.171
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ sex.gcse 0.624 0.000 NA NA 0.624 0.624
## 11 sex.gcse ~~ sex.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 13 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.789 0.000 NA NA 0.789 0.789
## 15 Zgcse ~1 0.209 0.000 NA NA 0.209 0.209
## 16 sex.gcse ~1 0.135 0.000 NA NA 0.135 0.135
modelb1.st_gapyear <- 'st_gapyear ~ SESscore + Zgcse'
modelb1.st_gapyearfit <- sem(modelb1.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(modelb1.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 6 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 3
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## SESscore 0.138 0.049 2.832 0.005 0.043 0.234
## Zgcse 0.052 0.050 1.030 0.303 -0.047 0.150
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.850 0.043 43.479 0.000 1.767 1.934
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.024
standardizedsolution(modelb1.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ SESscore 0.128 0.045 2.868 0.004 0.040 0.215
## 2 st_gapyear ~ Zgcse 0.048 0.047 1.032 0.302 -0.043 0.140
## 3 st_gapyear | t1 1.828 0.040 45.965 0.000 1.750 1.906
## 4 st_gapyear ~~ st_gapyear 0.976 0.012 80.658 0.000 0.952 0.999
## 5 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 7 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 8 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 9 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 11 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
modelb2.st_gapyear <- 'st_gapyear ~ SESscore + Zgcse + SES.gcse'
modelb2.st_gapyearfit <- sem(modelb2.st_gapyear, data = df_dummy, ordered = c("st_gapyear"), missing = "listwise")
summary(modelb2.st_gapyearfit, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 7 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 4
##
## Used Total
## Number of observations 3698 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## SESscore 0.135 0.049 2.723 0.006 0.038 0.232
## Zgcse 0.049 0.053 0.921 0.357 -0.056 0.154
## SES.gcse 0.015 0.053 0.284 0.776 -0.089 0.120
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.856 0.046 40.303 0.000 1.765 1.946
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.024
standardizedsolution(modelb2.st_gapyearfit)
## lhs op rhs est.std se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ SESscore 0.124 0.045 2.756 0.006 0.036 0.213
## 2 st_gapyear ~ Zgcse 0.046 0.050 0.923 0.356 -0.052 0.143
## 3 st_gapyear ~ SES.gcse 0.014 0.048 0.284 0.776 -0.081 0.108
## 4 st_gapyear | t1 1.834 0.044 41.498 0.000 1.747 1.920
## 5 st_gapyear ~~ st_gapyear 0.976 0.012 80.806 0.000 0.953 1.000
## 6 SESscore ~~ SESscore 1.000 0.000 NA NA 1.000 1.000
## 7 SESscore ~~ Zgcse 0.467 0.000 NA NA 0.467 0.467
## 8 SESscore ~~ SES.gcse 0.175 0.000 NA NA 0.175 0.175
## 9 Zgcse ~~ Zgcse 1.000 0.000 NA NA 1.000 1.000
## 10 Zgcse ~~ SES.gcse 0.037 0.000 NA NA 0.037 0.037
## 11 SES.gcse ~~ SES.gcse 1.000 0.000 NA NA 1.000 1.000
## 12 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 13 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.059 0.000 NA NA 0.059 0.059
## 15 Zgcse ~1 0.216 0.000 NA NA 0.216 0.216
## 16 SES.gcse ~1 0.463 0.000 NA NA 0.463 0.463
#get change in R2 for models with vs. w/0 moderation (modela1 vs. a2 and b1 vs b2)
(PE.modela1.st_gapyear <- parameterEstimates(modela1.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.078 0.082 -0.951 0.342 -0.238 0.083
## 2 st_gapyear ~ Zgcse 0.121 0.044 2.770 0.006 0.035 0.206
## 3 st_gapyear | t1 1.819 0.052 34.720 0.000 1.716 1.921
## 4 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 5 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 6 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 7 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 8 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 9 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 10 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 11 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 12 st_gapyear r2 st_gapyear 0.014 NA NA NA NA NA
PE.modela1.st_gapyear$est[PE.modela1.st_gapyear$op == "r2"]
## [1] 0.0141686
(PE.modela2.st_gapyear <- parameterEstimates(modela2.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ sex1 -0.030 0.087 -0.341 0.733 -0.199 0.140
## 2 st_gapyear ~ Zgcse 0.176 0.057 3.109 0.002 0.065 0.288
## 3 st_gapyear ~ sex.gcse -0.144 0.090 -1.609 0.108 -0.320 0.031
## 4 st_gapyear | t1 1.840 0.054 34.024 0.000 1.734 1.946
## 5 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 6 sex1 ~~ sex1 0.237 0.000 NA NA 0.237 0.237
## 7 sex1 ~~ Zgcse 0.006 0.000 NA NA 0.006 0.006
## 8 sex1 ~~ sex.gcse 0.050 0.000 NA NA 0.050 0.050
## 9 Zgcse ~~ Zgcse 0.893 0.000 NA NA 0.893 0.893
## 10 Zgcse ~~ sex.gcse 0.357 0.000 NA NA 0.357 0.357
## 11 sex.gcse ~~ sex.gcse 0.366 0.000 NA NA 0.366 0.366
## 12 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 13 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 14 sex1 ~1 0.384 0.000 NA NA 0.384 0.384
## 15 Zgcse ~1 0.198 0.000 NA NA 0.198 0.198
## 16 sex.gcse ~1 0.082 0.000 NA NA 0.082 0.082
## 17 st_gapyear r2 st_gapyear 0.018 NA NA NA NA NA
PE.modela2.st_gapyear$est[PE.modela2.st_gapyear$op == "r2"]
## [1] 0.01755005
(PE.modelb1.st_gapyear <- parameterEstimates(modelb1.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ SESscore 0.138 0.049 2.832 0.005 0.043 0.234
## 2 st_gapyear ~ Zgcse 0.052 0.050 1.030 0.303 -0.047 0.150
## 3 st_gapyear | t1 1.850 0.043 43.479 0.000 1.767 1.934
## 4 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 5 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 6 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 7 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 8 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 9 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 10 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 11 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 12 st_gapyear r2 st_gapyear 0.024 NA NA NA NA NA
PE.modelb1.st_gapyear$est[PE.modelb1.st_gapyear$op == "r2"]
## [1] 0.02442277
(PE.modelb2.st_gapyear <- parameterEstimates(modelb2.st_gapyearfit, rsquare = TRUE))
## lhs op rhs est se z pvalue ci.lower ci.upper
## 1 st_gapyear ~ SESscore 0.135 0.049 2.723 0.006 0.038 0.232
## 2 st_gapyear ~ Zgcse 0.049 0.053 0.921 0.357 -0.056 0.154
## 3 st_gapyear ~ SES.gcse 0.015 0.053 0.284 0.776 -0.089 0.120
## 4 st_gapyear | t1 1.856 0.046 40.303 0.000 1.765 1.946
## 5 st_gapyear ~~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 6 SESscore ~~ SESscore 0.874 0.000 NA NA 0.874 0.874
## 7 SESscore ~~ Zgcse 0.411 0.000 NA NA 0.411 0.411
## 8 SESscore ~~ SES.gcse 0.149 0.000 NA NA 0.149 0.149
## 9 Zgcse ~~ Zgcse 0.888 0.000 NA NA 0.888 0.888
## 10 Zgcse ~~ SES.gcse 0.032 0.000 NA NA 0.032 0.032
## 11 SES.gcse ~~ SES.gcse 0.833 0.000 NA NA 0.833 0.833
## 12 st_gapyear ~*~ st_gapyear 1.000 0.000 NA NA 1.000 1.000
## 13 st_gapyear ~1 0.000 0.000 NA NA 0.000 0.000
## 14 SESscore ~1 0.055 0.000 NA NA 0.055 0.055
## 15 Zgcse ~1 0.203 0.000 NA NA 0.203 0.203
## 16 SES.gcse ~1 0.422 0.000 NA NA 0.422 0.422
## 17 st_gapyear r2 st_gapyear 0.024 NA NA NA NA NA
PE.modelb2.st_gapyear$est[PE.modelb2.st_gapyear$op == "r2"]
## [1] 0.02371756
r2diffa.st_gapyear <- (PE.modela2.st_gapyear$est[PE.modela2.st_gapyear$op == "r2"] - PE.modela1.st_gapyear$est[PE.modela1.st_gapyear$op == "r2"])
print(r2diffa.st_gapyear) #difference modela1 vs a2, incremental explained variance by sexxGCSE
## [1] 0.003381456
r2diffb.st_gapyear <- (PE.modelb2.st_gapyear$est[PE.modelb2.st_gapyear$op == "r2"] - PE.modelb1.st_gapyear$est[PE.modelb1.st_gapyear$op == "r2"])
print(r2diffb.st_gapyear) #difference modelb1 vs b2, incremental explained variance by SESxGCSE
## [1] -0.0007052047
#Step 5: #Multi-group regression models
To test the robustness of our findings and reduce the likelihood of detecting spurious associations, we will fit a series of multi-group models to confirm the results of our hierarchical regression models across both samples of twins. We will use ANOVA tests to compare the fit of the ‘free’ model, where all parameters are unrestricted between both samples, to the restricted model, where all parameters are constrained to be equal. If the fit differences between the restricted and the unrestricted models are non-significant (pcorrected <.004), results will be interpreted as robust across both samples.
define model, fit without constrains for both groups (twin 1 and 2 according to random-variable), then constrain parameters to be equal and compare nested models with LRT
#linear: Zhqual, Zocprestige, Zinc, Zfina, Zwellb, Zanx, Zsdq, Zalc # logistic: u1cbenf11, status_bin # logistic w/ dummy coding: status1
#Linear multi-group regression models
rm(list=ls())
ls()
## character(0)
#read in both twins-dataset
df <- read.csv("/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_bothtwins.csv", header = T, strip.white = T,na.strings = c('NA', '', ' '
))
model2.hqual <- 'Zhqual ~ sex1 + SESscore + Zgcse'
multi.hqual.free <- sem(model2.hqual, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.hqual.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 28
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 4
## 1 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 2725.674
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -52425.772
## Loglikelihood unrestricted model (H1) -52425.772
##
## Akaike (AIC) 104907.545
## Bayesian (BIC) 105116.739
## Sample-size adjusted Bayesian (SABIC) 105027.758
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 -0.035 0.028 -1.242 0.214 -0.089 0.020
## SESscore 0.126 0.017 7.465 0.000 0.093 0.159
## Zgcse 0.530 0.016 32.219 0.000 0.498 0.562
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.581 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.106 0.017 -6.071 0.000 -0.140 -0.071
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.037 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.676 0.016 43.130 0.000 0.645 0.707
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.345
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 -0.038 0.029 -1.320 0.187 -0.093 0.018
## SESscore 0.133 0.017 7.900 0.000 0.100 0.167
## Zgcse 0.504 0.017 30.177 0.000 0.472 0.537
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual -0.099 0.018 -5.485 0.000 -0.134 -0.063
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.708 0.016 42.936 0.000 0.676 0.740
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.319
multi.hqual.cons <- sem(model2.hqual, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.hqual.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 29 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 28
## Number of equality constraints 4
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 4
## 1 4
##
## Model Test User Model:
##
## Test statistic 1.242
## Degrees of freedom 4
## P-value (Chi-square) 0.871
## Test statistic for each group:
## 0 0.605
## 1 0.636
##
## Model Test Baseline Model:
##
## Test statistic 2725.674
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.002
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.001
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -52426.393
## Loglikelihood unrestricted model (H1) -52425.772
##
## Akaike (AIC) 104900.786
## Bayesian (BIC) 105080.096
## Sample-size adjusted Bayesian (SABIC) 105003.827
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.009
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.014
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.004
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 (.p1.) -0.036 0.020 -1.823 0.068 -0.075 0.003
## SESscor (.p2.) 0.130 0.012 10.884 0.000 0.106 0.153
## Zgcse (.p3.) 0.517 0.012 44.140 0.000 0.494 0.540
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.581 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## SESscore ~~
## Zgcse 0.459 0.013 35.255 0.000 0.434 0.485
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual (.11.) -0.102 0.012 -8.167 0.000 -0.127 -0.078
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.036 0.012 -3.038 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.676 0.016 43.126 0.000 0.646 0.707
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.404 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.338
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zhqual ~
## sex1 (.p1.) -0.036 0.020 -1.823 0.068 -0.075 0.003
## SESscor (.p2.) 0.130 0.012 10.884 0.000 0.106 0.153
## Zgcse (.p3.) 0.517 0.012 44.140 0.000 0.494 0.540
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual (.11.) -0.102 0.012 -8.167 0.000 -0.127 -0.078
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zhqual 0.708 0.016 42.933 0.000 0.676 0.741
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zhqual 0.327
lavTestLRT(multi.hqual.free, multi.hqual.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.hqual.free 0 104908 105117 0.0000
## multi.hqual.cons 4 104901 105080 1.2417 1.2417 0 4 0.8712
#anova(multi.hqual.free, multi.hqual.cons) #<--- does exactly the same thing (Chi2 Diff test)
model3.degree <- 'Zdegree ~ sex1 + SESscore + Zgcse'
multi.degree.free <- sem(model3.degree, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.degree.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 27 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 28
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 4
## 1 4
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 287.580
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -48162.041
## Loglikelihood unrestricted model (H1) -48162.041
##
## Akaike (AIC) 96380.081
## Bayesian (BIC) 96589.276
## Sample-size adjusted Bayesian (SABIC) 96500.295
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 0.013 0.047 0.276 0.783 -0.080 0.106
## SESscore -0.019 0.028 -0.676 0.499 -0.075 0.036
## Zgcse 0.371 0.033 11.141 0.000 0.306 0.437
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.587 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## SESscore ~~
## Zgcse 0.459 0.013 35.248 0.000 0.434 0.485
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.209 0.034 -6.227 0.000 -0.274 -0.143
## sex1 0.469 0.006 75.701 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.025 0.002 -0.058 -0.012
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.926 0.031 29.774 0.000 0.865 0.987
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.410 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.979 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.124
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 -0.080 0.048 -1.672 0.095 -0.173 0.014
## SESscore 0.014 0.028 0.505 0.613 -0.041 0.070
## Zgcse 0.375 0.033 11.366 0.000 0.310 0.439
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.435 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree -0.170 0.032 -5.307 0.000 -0.232 -0.107
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.917 0.031 29.792 0.000 0.857 0.978
## sex1 0.249 0.004 56.957 0.000 0.241 0.258
## SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.957 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.139
multi.degree.cons <- sem(model3.degree, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.degree.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 37 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 28
## Number of equality constraints 4
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 4
## 1 4
##
## Model Test User Model:
##
## Test statistic 2.879
## Degrees of freedom 4
## P-value (Chi-square) 0.578
## Test statistic for each group:
## 0 1.419
## 1 1.460
##
## Model Test Baseline Model:
##
## Test statistic 287.580
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.006
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.006
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -48163.480
## Loglikelihood unrestricted model (H1) -48162.041
##
## Akaike (AIC) 96374.960
## Bayesian (BIC) 96554.270
## Sample-size adjusted Bayesian (SABIC) 96478.001
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.016
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.032
## P-value H_0: Robust RMSEA <= 0.050 0.997
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.008
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 (.p1.) -0.033 0.034 -0.980 0.327 -0.099 0.033
## SESscor (.p2.) -0.003 0.020 -0.130 0.896 -0.042 0.037
## Zgcse (.p3.) 0.372 0.023 15.877 0.000 0.326 0.418
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.587 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## SESscore ~~
## Zgcse 0.459 0.013 35.248 0.000 0.434 0.485
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree (.11.) -0.189 0.023 -8.156 0.000 -0.234 -0.143
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.035 0.012 -3.026 0.002 -0.058 -0.012
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.927 0.031 29.762 0.000 0.866 0.988
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.409 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.130
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zdegree ~
## sex1 (.p1.) -0.033 0.034 -0.980 0.327 -0.099 0.033
## SESscor (.p2.) -0.003 0.020 -0.130 0.896 -0.042 0.037
## Zgcse (.p3.) 0.372 0.023 15.877 0.000 0.326 0.418
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.434 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## SESscore ~~
## Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree (.11.) -0.189 0.023 -8.156 0.000 -0.234 -0.143
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zdegree 0.918 0.031 29.779 0.000 0.858 0.979
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.312 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
##
## R-Square:
## Estimate
## Zdegree 0.131
lavTestLRT(multi.degree.free, multi.degree.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.degree.free 0 96380 96589 0.0000
## multi.degree.cons 4 96375 96554 2.8791 2.879 0 4 0.5783
model3.ocprestige <- 'Zsoc ~ sex1 + SESscore + Zgcse + Zhqual'
multi.ocprestige.free <- sem(model3.ocprestige, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.ocprestige.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 415.912
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -57116.411
## Loglikelihood unrestricted model (H1) -57116.411
##
## Akaike (AIC) 114312.821
## Bayesian (BIC) 114611.671
## Sample-size adjusted Bayesian (SABIC) 114484.555
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.037 0.046 0.794 0.427 -0.054 0.128
## SESscore 0.061 0.029 2.125 0.034 0.005 0.117
## Zgcse 0.218 0.030 7.156 0.000 0.158 0.278
## Zhqual 0.127 0.026 4.890 0.000 0.076 0.178
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.578 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.911 0.004 -0.038 -0.007
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.236 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.588 0.018 33.319 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.044 0.029 1.493 0.135 -0.014 0.101
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.035 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.946 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.889 0.030 29.712 0.000 0.830 0.947
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.200 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zsoc 0.117
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 0.183 0.048 3.824 0.000 0.089 0.276
## SESscore 0.046 0.029 1.606 0.108 -0.010 0.102
## Zgcse 0.191 0.031 6.067 0.000 0.129 0.252
## Zhqual 0.168 0.025 6.601 0.000 0.118 0.218
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.428 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.610 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.301 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.575 0.000 0.530 0.601
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc -0.000 0.030 -0.003 0.998 -0.058 0.058
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.532 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.883 0.030 29.023 0.000 0.823 0.942
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.563 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zsoc 0.122
multi.ocprestige.cons <- sem(model3.ocprestige, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.ocprestige.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 36 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 5.905
## Degrees of freedom 5
## P-value (Chi-square) 0.316
## Test statistic for each group:
## 0 2.866
## 1 3.039
##
## Model Test Baseline Model:
##
## Test statistic 415.912
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.998
## Tucker-Lewis Index (TLI) 0.996
##
## Robust Comparative Fit Index (CFI) 0.997
## Robust Tucker-Lewis Index (TLI) 0.995
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -57119.363
## Loglikelihood unrestricted model (H1) -57116.411
##
## Akaike (AIC) 114308.727
## Bayesian (BIC) 114570.220
## Sample-size adjusted Bayesian (SABIC) 114458.994
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.005
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.019
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.013
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.039
## P-value H_0: Robust RMSEA <= 0.050 0.995
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.009
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 (.p1.) 0.107 0.033 3.214 0.001 0.042 0.173
## SESscor (.p2.) 0.053 0.020 2.620 0.009 0.013 0.093
## Zgcse (.p3.) 0.205 0.022 9.378 0.000 0.162 0.248
## Zhqual (.p4.) 0.147 0.018 8.106 0.000 0.112 0.183
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.578 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.913 0.004 -0.038 -0.007
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.237 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.588 0.018 33.319 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc (.16.) 0.022 0.021 1.054 0.292 -0.019 0.063
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.035 0.012 -3.035 0.002 -0.058 -0.013
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.947 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.890 0.030 29.687 0.000 0.831 0.949
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.202 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zsoc 0.118
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsoc ~
## sex1 (.p1.) 0.107 0.033 3.214 0.001 0.042 0.173
## SESscor (.p2.) 0.053 0.020 2.620 0.009 0.013 0.093
## Zgcse (.p3.) 0.205 0.022 9.378 0.000 0.162 0.248
## Zhqual (.p4.) 0.147 0.018 8.106 0.000 0.112 0.183
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.608 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.298 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.571 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc (.16.) 0.022 0.021 1.054 0.292 -0.019 0.063
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.930 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.529 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsoc 0.884 0.030 28.999 0.000 0.825 0.944
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.564 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zsoc 0.117
lavTestLRT(multi.ocprestige.free, multi.ocprestige.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff
## multi.ocprestige.free 0 114313 114612 0.0000
## multi.ocprestige.cons 5 114309 114570 5.9055 5.9055 0.0052823 5
## Pr(>Chisq)
## multi.ocprestige.free
## multi.ocprestige.cons 0.3155
model3.inc <- 'Zinc ~ sex1 + SESscore + Zgcse + Zhqual'
multi.inc.free <- sem(model3.inc, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.inc.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 33 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 269.817
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -57680.411
## Loglikelihood unrestricted model (H1) -57680.411
##
## Akaike (AIC) 115440.822
## Bayesian (BIC) 115739.672
## Sample-size adjusted Bayesian (SABIC) 115612.556
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.405 0.046 8.869 0.000 0.316 0.495
## SESscore 0.040 0.028 1.427 0.154 -0.015 0.096
## Zgcse 0.180 0.030 5.959 0.000 0.121 0.239
## Zhqual -0.018 0.026 -0.677 0.498 -0.069 0.033
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.584 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.922 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.225 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.589 0.018 33.329 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.144 0.029 -5.011 0.000 -0.201 -0.088
## sex1 0.469 0.006 75.701 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.035 0.002 -0.058 -0.013
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.950 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.931 0.030 30.966 0.000 0.872 0.990
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.188 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zinc 0.073
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 0.388 0.046 8.349 0.000 0.297 0.479
## SESscore 0.041 0.028 1.482 0.138 -0.013 0.096
## Zgcse 0.162 0.030 5.404 0.000 0.103 0.221
## Zhqual 0.020 0.025 0.802 0.423 -0.029 0.069
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.428 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.607 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.279 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.552 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc -0.121 0.029 -4.209 0.000 -0.177 -0.065
## sex1 0.474 0.006 76.502 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.517 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.931 0.030 30.666 0.000 0.871 0.990
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.569 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zinc 0.073
multi.inc.cons <- sem(model3.inc, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.inc.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 38 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 1.285
## Degrees of freedom 5
## P-value (Chi-square) 0.936
## Test statistic for each group:
## 0 0.661
## 1 0.624
##
## Model Test Baseline Model:
##
## Test statistic 269.817
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.023
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.022
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -57681.054
## Loglikelihood unrestricted model (H1) -57680.411
##
## Akaike (AIC) 115432.107
## Bayesian (BIC) 115693.601
## Sample-size adjusted Bayesian (SABIC) 115582.374
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.004
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.004
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.004
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 (.p1.) 0.397 0.033 12.172 0.000 0.333 0.461
## SESscor (.p2.) 0.040 0.020 2.033 0.042 0.001 0.079
## Zgcse (.p3.) 0.170 0.021 8.001 0.000 0.128 0.212
## Zhqual (.p4.) 0.002 0.018 0.109 0.913 -0.033 0.037
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.584 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.922 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.227 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.589 0.018 33.329 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc (.16.) -0.132 0.020 -6.511 0.000 -0.172 -0.092
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.035 0.012 -3.035 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.950 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.931 0.030 30.962 0.000 0.873 0.990
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.188 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zinc 0.072
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zinc ~
## sex1 (.p1.) 0.397 0.033 12.172 0.000 0.333 0.461
## SESscor (.p2.) 0.040 0.020 2.033 0.042 0.001 0.079
## Zgcse (.p3.) 0.170 0.021 8.001 0.000 0.128 0.212
## Zhqual (.p4.) 0.002 0.018 0.109 0.913 -0.033 0.037
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.428 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.274 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.549 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc (.16.) -0.132 0.020 -6.511 0.000 -0.172 -0.092
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.515 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zinc 0.931 0.030 30.662 0.000 0.871 0.991
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.573 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zinc 0.073
lavTestLRT(multi.inc.free, multi.inc.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.inc.free 0 115441 115740 0.0000
## multi.inc.cons 5 115432 115694 1.2853 1.2853 0 5 0.9364
model3.mon <- 'Zmon ~ sex1 + SESscore + Zgcse + Zhqual'
multi.mon.free <- sem(model3.mon, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.mon.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 22 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 127.475
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62824.287
## Loglikelihood unrestricted model (H1) -62824.287
##
## Akaike (AIC) 125728.575
## Bayesian (BIC) 126027.424
## Sample-size adjusted Bayesian (SABIC) 125900.308
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.134 0.034 -3.982 0.000 -0.200 -0.068
## SESscore -0.092 0.020 -4.505 0.000 -0.132 -0.052
## Zgcse 0.099 0.022 4.411 0.000 0.055 0.143
## Zhqual -0.013 0.020 -0.637 0.524 -0.052 0.027
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.582 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.919 0.004 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.255 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.252 0.000 0.323 0.383
## Zgcse ~~
## Zhqual 0.588 0.018 33.325 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.035 0.021 1.666 0.096 -0.006 0.077
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.036 0.012 -3.047 0.002 -0.059 -0.013
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.947 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.987 0.023 43.089 0.000 0.942 1.032
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.403 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.191 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zmon 0.014
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 -0.230 0.034 -6.828 0.000 -0.295 -0.164
## SESscore -0.094 0.020 -4.614 0.000 -0.133 -0.054
## Zgcse 0.084 0.022 3.806 0.000 0.041 0.127
## Zhqual 0.024 0.020 1.209 0.227 -0.015 0.062
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.423 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.278 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.554 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.077 0.021 3.618 0.000 0.035 0.119
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.924 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.517 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.978 0.023 42.773 0.000 0.933 1.023
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.874 0.016 56.325 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.571 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zmon 0.024
multi.mon.cons <- sem(model3.mon, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.mon.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 5.858
## Degrees of freedom 5
## P-value (Chi-square) 0.320
## Test statistic for each group:
## 0 2.946
## 1 2.912
##
## Model Test Baseline Model:
##
## Test statistic 127.475
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.993
## Tucker-Lewis Index (TLI) 0.989
##
## Robust Comparative Fit Index (CFI) 0.993
## Robust Tucker-Lewis Index (TLI) 0.988
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62827.216
## Loglikelihood unrestricted model (H1) -62824.287
##
## Akaike (AIC) 125724.432
## Bayesian (BIC) 125985.926
## Sample-size adjusted Bayesian (SABIC) 125874.699
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.005
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.019
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.007
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.026
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.007
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 (.p1.) -0.182 0.024 -7.636 0.000 -0.229 -0.135
## SESscor (.p2.) -0.093 0.014 -6.442 0.000 -0.121 -0.065
## Zgcse (.p3.) 0.091 0.016 5.763 0.000 0.060 0.121
## Zhqual (.p4.) 0.006 0.014 0.420 0.674 -0.022 0.033
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.581 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.921 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.255 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.253 0.000 0.323 0.383
## Zgcse ~~
## Zhqual 0.589 0.018 33.330 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon (.16.) 0.056 0.015 3.735 0.000 0.027 0.086
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.036 0.012 -3.047 0.002 -0.059 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.949 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.988 0.023 43.073 0.000 0.943 1.033
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.403 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.188 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zmon 0.018
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zmon ~
## sex1 (.p1.) -0.182 0.024 -7.636 0.000 -0.229 -0.135
## SESscor (.p2.) -0.093 0.014 -6.442 0.000 -0.121 -0.065
## Zgcse (.p3.) 0.091 0.016 5.763 0.000 0.060 0.121
## Zhqual (.p4.) 0.006 0.014 0.420 0.674 -0.022 0.033
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.423 0.000 0.422 0.472
## Zhqual 0.342 0.015 22.277 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.551 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon (.16.) 0.056 0.015 3.735 0.000 0.027 0.086
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.924 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.517 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zmon 0.979 0.023 42.757 0.000 0.934 1.024
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.874 0.016 56.326 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.573 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zmon 0.018
lavTestLRT(multi.mon.free, multi.mon.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.mon.free 0 125729 126027 0.0000
## multi.mon.cons 5 125724 125986 5.8577 5.8577 0.0051409 5 0.3203
model3.fina <- 'Zfina ~ sex1 + SESscore + Zgcse + Zhqual'
multi.fina.free <- sem(model3.fina, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.fina.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 90.109
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62845.808
## Loglikelihood unrestricted model (H1) -62845.808
##
## Akaike (AIC) 125771.617
## Bayesian (BIC) 126070.466
## Sample-size adjusted Bayesian (SABIC) 125943.350
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.080 0.034 2.382 0.017 0.014 0.146
## SESscore -0.036 0.020 -1.761 0.078 -0.076 0.004
## Zgcse 0.107 0.022 4.778 0.000 0.063 0.151
## Zhqual -0.132 0.020 -6.575 0.000 -0.172 -0.093
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.578 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.925 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.255 0.000 0.434 0.485
## Zhqual 0.352 0.015 23.230 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.588 0.018 33.310 0.000 0.553 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.051 0.021 -2.402 0.016 -0.092 -0.009
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.038 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.941 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.985 0.023 43.079 0.000 0.940 1.029
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.404 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.032 0.024 43.208 0.000 0.986 1.079
##
## R-Square:
## Estimate
## Zfina 0.015
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 0.063 0.034 1.863 0.063 -0.003 0.129
## SESscore -0.069 0.020 -3.376 0.001 -0.109 -0.029
## Zgcse 0.084 0.022 3.788 0.000 0.040 0.127
## Zhqual -0.079 0.020 -4.006 0.000 -0.118 -0.040
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.425 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.595 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.428 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.274 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.549 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina -0.038 0.021 -1.768 0.077 -0.080 0.004
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.918 0.004 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.527 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.990 0.023 42.784 0.000 0.945 1.036
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.322 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.579 0.000 0.991 1.087
##
## R-Square:
## Estimate
## Zfina 0.010
multi.fina.cons <- sem(model3.fina, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.fina.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 34 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 7
##
## Model Test User Model:
##
## Test statistic 4.660
## Degrees of freedom 5
## P-value (Chi-square) 0.459
## Test statistic for each group:
## 0 2.362
## 1 2.298
##
## Model Test Baseline Model:
##
## Test statistic 90.109
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.007
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.010
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62848.138
## Loglikelihood unrestricted model (H1) -62845.808
##
## Akaike (AIC) 125766.277
## Bayesian (BIC) 126027.770
## Sample-size adjusted Bayesian (SABIC) 125916.544
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.017
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.022
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.004
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 (.p1.) 0.072 0.024 3.001 0.003 0.025 0.118
## SESscor (.p2.) -0.052 0.014 -3.627 0.000 -0.081 -0.024
## Zgcse (.p3.) 0.095 0.016 6.036 0.000 0.064 0.126
## Zhqual (.p4.) -0.105 0.014 -7.457 0.000 -0.133 -0.078
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.577 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.924 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.255 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.232 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.588 0.018 33.313 0.000 0.553 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina (.16.) -0.044 0.015 -2.945 0.003 -0.074 -0.015
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.036 0.012 -3.038 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.942 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.985 0.023 43.068 0.000 0.940 1.030
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.404 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.204 0.000 0.986 1.079
##
## R-Square:
## Estimate
## Zfina 0.012
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zfina ~
## sex1 (.p1.) 0.072 0.024 3.001 0.003 0.025 0.118
## SESscor (.p2.) -0.052 0.014 -3.627 0.000 -0.081 -0.024
## Zgcse (.p3.) 0.095 0.016 6.036 0.000 0.064 0.126
## Zhqual (.p4.) -0.105 0.014 -7.457 0.000 -0.133 -0.078
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.591 0.010 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.429 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.273 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.550 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina (.16.) -0.044 0.015 -2.945 0.003 -0.074 -0.015
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.920 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.531 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zfina 0.991 0.023 42.770 0.000 0.945 1.036
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.321 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.581 0.000 0.991 1.087
##
## R-Square:
## Estimate
## Zfina 0.012
lavTestLRT(multi.fina.free, multi.fina.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.fina.free 0 125772 126070 0.0000
## multi.fina.cons 5 125766 126028 4.6603 4.6603 0 5 0.4587
model3.wellb <- 'Zwellb ~ sex1 + SESscore + Zgcse + Zhqual'
multi.wellb.free <- sem(model3.wellb, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.wellb.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 251.998
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -63003.246
## Loglikelihood unrestricted model (H1) -63003.246
##
## Akaike (AIC) 126086.491
## Bayesian (BIC) 126385.341
## Sample-size adjusted Bayesian (SABIC) 126258.225
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.312 0.033 9.476 0.000 0.248 0.377
## SESscore 0.013 0.020 0.656 0.512 -0.026 0.053
## Zgcse 0.105 0.022 4.787 0.000 0.062 0.148
## Zhqual 0.009 0.020 0.446 0.656 -0.030 0.048
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.583 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.922 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.233 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.589 0.018 33.330 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.140 0.021 -6.767 0.000 -0.181 -0.100
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.038 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.952 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.964 0.022 43.531 0.000 0.921 1.008
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.187 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zwellb 0.036
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 0.266 0.033 8.034 0.000 0.201 0.331
## SESscore 0.006 0.020 0.316 0.752 -0.033 0.045
## Zgcse 0.085 0.022 3.953 0.000 0.043 0.128
## Zhqual 0.048 0.019 2.455 0.014 0.010 0.086
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.600 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.281 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.558 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb -0.119 0.021 -5.712 0.000 -0.160 -0.078
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.522 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.969 0.022 43.322 0.000 0.925 1.013
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.569 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zwellb 0.031
multi.wellb.cons <- sem(model3.wellb, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.wellb.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 8
##
## Model Test User Model:
##
## Test statistic 2.986
## Degrees of freedom 5
## P-value (Chi-square) 0.702
## Test statistic for each group:
## 0 1.525
## 1 1.461
##
## Model Test Baseline Model:
##
## Test statistic 251.998
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.013
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.014
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -63004.739
## Loglikelihood unrestricted model (H1) -63003.246
##
## Akaike (AIC) 126079.477
## Bayesian (BIC) 126340.971
## Sample-size adjusted Bayesian (SABIC) 126229.744
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.013
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.018
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.004
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 (.p1.) 0.289 0.023 12.376 0.000 0.243 0.335
## SESscor (.p2.) 0.010 0.014 0.690 0.490 -0.018 0.037
## Zgcse (.p3.) 0.095 0.015 6.143 0.000 0.064 0.125
## Zhqual (.p4.) 0.029 0.014 2.076 0.038 0.002 0.056
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.582 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.923 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.236 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.589 0.018 33.332 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb (.16.) -0.130 0.015 -8.815 0.000 -0.158 -0.101
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.035 0.012 -3.038 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.960 0.000 -0.158 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.965 0.022 43.523 0.000 0.921 1.008
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.186 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zwellb 0.033
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zwellb ~
## sex1 (.p1.) 0.289 0.023 12.376 0.000 0.243 0.335
## SESscor (.p2.) 0.010 0.014 0.690 0.490 -0.018 0.037
## Zgcse (.p3.) 0.095 0.015 6.143 0.000 0.064 0.125
## Zhqual (.p4.) 0.029 0.014 2.076 0.038 0.002 0.056
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.602 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.278 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.554 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb (.16.) -0.130 0.015 -8.815 0.000 -0.158 -0.101
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.520 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zwellb 0.970 0.022 43.314 0.000 0.926 1.014
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.571 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zwellb 0.033
lavTestLRT(multi.wellb.free, multi.wellb.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.wellb.free 0 126086 126385 0.000
## multi.wellb.cons 5 126079 126341 2.986 2.986 0 5 0.7022
model3.anx <- 'Zanx ~ sex1 + SESscore + Zgcse + Zhqual'
multi.anx.free <- sem(model3.anx, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.anx.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 27 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 8
## 1 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 190.721
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62020.762
## Loglikelihood unrestricted model (H1) -62020.762
##
## Akaike (AIC) 124121.524
## Bayesian (BIC) 124420.373
## Sample-size adjusted Bayesian (SABIC) 124293.257
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.339 0.035 -9.644 0.000 -0.408 -0.270
## SESscore 0.006 0.021 0.285 0.776 -0.036 0.048
## Zgcse -0.060 0.024 -2.535 0.011 -0.106 -0.014
## Zhqual 0.008 0.022 0.368 0.713 -0.036 0.052
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.580 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.921 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.231 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.589 0.018 33.329 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.136 0.022 6.260 0.000 0.094 0.179
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.035 0.012 -3.037 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.949 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.971 0.024 41.237 0.000 0.925 1.017
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.188 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zanx 0.030
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 -0.334 0.035 -9.542 0.000 -0.402 -0.265
## SESscore -0.003 0.021 -0.161 0.872 -0.044 0.038
## Zgcse -0.003 0.023 -0.145 0.884 -0.048 0.041
## Zhqual -0.010 0.021 -0.479 0.632 -0.051 0.031
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.432 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.274 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.550 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.124 0.022 5.753 0.000 0.082 0.167
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.515 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.973 0.024 41.406 0.000 0.927 1.020
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.573 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zanx 0.028
multi.anx.cons <- sem(model3.anx, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.anx.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 31 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 8
## 1 8
##
## Model Test User Model:
##
## Test statistic 3.246
## Degrees of freedom 5
## P-value (Chi-square) 0.662
## Test statistic for each group:
## 0 1.663
## 1 1.583
##
## Model Test Baseline Model:
##
## Test statistic 190.721
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.015
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.015
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62022.385
## Loglikelihood unrestricted model (H1) -62020.762
##
## Akaike (AIC) 124114.770
## Bayesian (BIC) 124376.263
## Sample-size adjusted Bayesian (SABIC) 124265.037
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.014
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.020
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.005
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 (.p1.) -0.335 0.025 -13.525 0.000 -0.384 -0.287
## SESscor (.p2.) 0.001 0.015 0.074 0.941 -0.028 0.030
## Zgcse (.p3.) -0.031 0.016 -1.872 0.061 -0.063 0.001
## Zhqual (.p4.) -0.002 0.015 -0.105 0.917 -0.032 0.029
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.581 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.922 0.003 -0.038 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.254 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.232 0.000 0.323 0.382
## Zgcse ~~
## Zhqual 0.589 0.018 33.329 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx (.16.) 0.130 0.015 8.452 0.000 0.099 0.160
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.035 0.012 -3.037 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.950 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.971 0.024 41.227 0.000 0.925 1.018
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.405 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.188 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zanx 0.028
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zanx ~
## sex1 (.p1.) -0.335 0.025 -13.525 0.000 -0.384 -0.287
## SESscor (.p2.) 0.001 0.015 0.074 0.941 -0.028 0.030
## Zgcse (.p3.) -0.031 0.016 -1.872 0.061 -0.063 0.001
## Zhqual (.p4.) -0.002 0.015 -0.105 0.917 -0.032 0.029
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.429 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.604 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.274 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.549 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx (.16.) 0.130 0.015 8.452 0.000 0.099 0.160
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.928 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.515 0.000 -0.153 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zanx 0.974 0.024 41.397 0.000 0.928 1.020
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.318 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.574 0.000 0.992 1.087
##
## R-Square:
## Estimate
## Zanx 0.028
lavTestLRT(multi.anx.free, multi.anx.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.anx.free 0 124122 124420 0.0000
## multi.anx.cons 5 124115 124376 3.2462 3.2462 0 5 0.6621
model3.sdq <- 'Zsdq ~ sex1 + SESscore + Zgcse + Zhqual'
multi.sdq.free <- sem(model3.sdq, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.sdq.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 484.210
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62894.234
## Loglikelihood unrestricted model (H1) -62894.234
##
## Akaike (AIC) 125868.468
## Bayesian (BIC) 126167.318
## Sample-size adjusted Bayesian (SABIC) 126040.202
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.171 0.032 -5.255 0.000 -0.234 -0.107
## SESscore -0.038 0.020 -1.897 0.058 -0.076 0.001
## Zgcse -0.175 0.022 -8.064 0.000 -0.217 -0.132
## Zhqual -0.070 0.020 -3.559 0.000 -0.108 -0.031
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.586 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.936 0.003 -0.039 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.256 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.239 0.000 0.323 0.383
## Zgcse ~~
## Zhqual 0.589 0.018 33.344 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.101 0.020 4.961 0.000 0.061 0.142
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.036 0.012 -3.040 0.002 -0.058 -0.013
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.127 0.016 -7.978 0.000 -0.158 -0.096
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.939 0.022 43.547 0.000 0.896 0.981
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.402 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.034 0.024 43.179 0.000 0.987 1.080
##
## R-Square:
## Estimate
## Zsdq 0.064
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 -0.197 0.033 -6.046 0.000 -0.260 -0.133
## SESscore -0.010 0.020 -0.489 0.625 -0.048 0.029
## Zgcse -0.163 0.021 -7.685 0.000 -0.205 -0.122
## Zhqual -0.105 0.019 -5.520 0.000 -0.143 -0.068
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.430 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.594 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.433 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.287 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.574 0.000 0.530 0.601
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.108 0.020 5.268 0.000 0.068 0.148
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.530 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.936 0.022 43.319 0.000 0.894 0.979
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.565 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zsdq 0.067
multi.sdq.cons <- sem(model3.sdq, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.sdq.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 28 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 7
## 1 8
##
## Model Test User Model:
##
## Test statistic 2.659
## Degrees of freedom 5
## P-value (Chi-square) 0.752
## Test statistic for each group:
## 0 1.354
## 1 1.305
##
## Model Test Baseline Model:
##
## Test statistic 484.210
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.008
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.008
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -62895.563
## Loglikelihood unrestricted model (H1) -62894.234
##
## Akaike (AIC) 125861.127
## Bayesian (BIC) 126122.620
## Sample-size adjusted Bayesian (SABIC) 126011.394
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.012
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.016
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.003
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 (.p1.) -0.184 0.023 -7.987 0.000 -0.229 -0.139
## SESscor (.p2.) -0.023 0.014 -1.682 0.092 -0.051 0.004
## Zgcse (.p3.) -0.169 0.015 -11.134 0.000 -0.199 -0.139
## Zhqual (.p4.) -0.088 0.014 -6.436 0.000 -0.115 -0.061
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.584 0.010 0.004 0.027
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.941 0.003 -0.039 -0.008
## SESscore ~~
## Zgcse 0.459 0.013 35.255 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.242 0.000 0.323 0.383
## Zgcse ~~
## Zhqual 0.589 0.018 33.349 0.000 0.554 0.624
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq (.16.) 0.105 0.014 7.229 0.000 0.076 0.133
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.036 0.012 -3.039 0.002 -0.058 -0.013
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.127 0.016 -7.986 0.000 -0.158 -0.096
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.939 0.022 43.539 0.000 0.897 0.981
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.403 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.034 0.024 43.177 0.000 0.987 1.081
##
## R-Square:
## Estimate
## Zsdq 0.065
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zsdq ~
## sex1 (.p1.) -0.184 0.023 -7.987 0.000 -0.229 -0.139
## SESscor (.p2.) -0.023 0.014 -1.682 0.092 -0.051 0.004
## Zgcse (.p3.) -0.169 0.015 -11.134 0.000 -0.199 -0.139
## Zhqual (.p4.) -0.088 0.014 -6.436 0.000 -0.115 -0.061
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.431 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.595 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.434 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.281 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.569 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq (.16.) 0.105 0.014 7.229 0.000 0.076 0.133
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.929 0.003 -0.057 -0.011
## Zgcse -0.000 0.012 -0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.527 0.000 -0.153 -0.090
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zsdq 0.937 0.022 43.313 0.000 0.894 0.979
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.317 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.040 0.024 42.567 0.000 0.992 1.088
##
## R-Square:
## Estimate
## Zsdq 0.065
lavTestLRT(multi.sdq.free, multi.sdq.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.sdq.free 0 125868 126167 0.0000
## multi.sdq.cons 5 125861 126123 2.6586 2.6586 0 5 0.7524
model3.alc <- 'Zalc ~ sex1 + SESscore + Zgcse + Zhqual'
multi.alc.free <- sem(model3.alc, data = df, group = "random", missing = "fiml", fixed.x = FALSE)
summary(multi.alc.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 8
## 1 8
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
## Test statistic for each group:
## 0 0.000
## 1 0.000
##
## Model Test Baseline Model:
##
## Test statistic 170.978
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.000
##
## Robust Comparative Fit Index (CFI) 1.000
## Robust Tucker-Lewis Index (TLI) 1.000
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -61304.137
## Loglikelihood unrestricted model (H1) -61304.137
##
## Akaike (AIC) 122688.274
## Bayesian (BIC) 122987.123
## Sample-size adjusted Bayesian (SABIC) 122860.007
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: RMSEA <= 0.050 NA
## P-value H_0: RMSEA >= 0.080 NA
##
## Robust RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.000
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.256 0.036 7.045 0.000 0.185 0.327
## SESscore 0.081 0.022 3.667 0.000 0.038 0.125
## Zgcse 0.024 0.024 0.995 0.320 -0.023 0.072
## Zhqual 0.057 0.023 2.484 0.013 0.012 0.103
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.581 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.908 0.004 -0.038 -0.007
## SESscore ~~
## Zgcse 0.459 0.013 35.252 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.242 0.000 0.323 0.383
## Zgcse ~~
## Zhqual 0.589 0.018 33.330 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.111 0.023 -4.862 0.000 -0.155 -0.066
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscore -0.036 0.012 -3.039 0.002 -0.058 -0.013
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.946 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.968 0.024 39.670 0.000 0.921 1.016
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.407 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.190 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zalc 0.032
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 0.224 0.036 6.159 0.000 0.153 0.295
## SESscore 0.109 0.022 5.007 0.000 0.067 0.152
## Zgcse -0.033 0.024 -1.386 0.166 -0.080 0.014
## Zhqual 0.027 0.022 1.206 0.228 -0.017 0.071
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.597 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.438 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.280 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.542 0.000 0.530 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc -0.085 0.023 -3.736 0.000 -0.129 -0.040
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscore -0.034 0.012 -2.922 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.507 0.000 -0.152 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.977 0.025 39.799 0.000 0.929 1.025
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.313 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.578 0.000 0.991 1.087
##
## R-Square:
## Estimate
## Zalc 0.023
multi.alc.cons <- sem(model3.alc, data = df, group = "random", group.equal = c("intercepts", "regressions"), missing = "fiml", fixed.x = FALSE)
summary(multi.alc.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 33 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 40
## Number of equality constraints 5
##
## Number of observations per group:
## 0 6493
## 1 6488
## Number of missing patterns per group:
## 0 8
## 1 8
##
## Model Test User Model:
##
## Test statistic 7.234
## Degrees of freedom 5
## P-value (Chi-square) 0.204
## Test statistic for each group:
## 0 3.674
## 1 3.559
##
## Model Test Baseline Model:
##
## Test statistic 170.978
## Degrees of freedom 8
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.986
## Tucker-Lewis Index (TLI) 0.978
##
## Robust Comparative Fit Index (CFI) 0.983
## Robust Tucker-Lewis Index (TLI) 0.972
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -61307.754
## Loglikelihood unrestricted model (H1) -61304.137
##
## Akaike (AIC) 122685.507
## Bayesian (BIC) 122947.001
## Sample-size adjusted Bayesian (SABIC) 122835.774
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.008
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.020
## P-value H_0: RMSEA <= 0.050 1.000
## P-value H_0: RMSEA >= 0.080 0.000
##
## Robust RMSEA 0.014
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.032
## P-value H_0: Robust RMSEA <= 0.050 1.000
## P-value H_0: Robust RMSEA >= 0.080 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.009
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 (.p1.) 0.239 0.026 9.304 0.000 0.189 0.290
## SESscor (.p2.) 0.096 0.016 6.183 0.000 0.066 0.127
## Zgcse (.p3.) -0.005 0.017 -0.283 0.777 -0.038 0.029
## Zhqual (.p4.) 0.042 0.016 2.594 0.009 0.010 0.073
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.015 0.006 2.581 0.010 0.004 0.026
## Zgcse -0.031 0.006 -4.947 0.000 -0.043 -0.019
## Zhqual -0.023 0.008 -2.911 0.004 -0.038 -0.007
## SESscore ~~
## Zgcse 0.459 0.013 35.253 0.000 0.434 0.485
## Zhqual 0.353 0.015 23.241 0.000 0.323 0.383
## Zgcse ~~
## Zhqual 0.589 0.018 33.332 0.000 0.554 0.623
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc (.16.) -0.097 0.016 -6.042 0.000 -0.129 -0.066
## sex1 0.469 0.006 75.700 0.000 0.457 0.481
## SESscor -0.036 0.012 -3.040 0.002 -0.058 -0.013
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.126 0.016 -7.949 0.000 -0.157 -0.095
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.970 0.024 39.649 0.000 0.922 1.018
## sex1 0.249 0.004 56.978 0.000 0.240 0.258
## SESscore 0.874 0.015 56.407 0.000 0.844 0.904
## Zgcse 1.000 0.018 56.978 0.000 0.965 1.034
## Zhqual 1.033 0.024 43.187 0.000 0.986 1.080
##
## R-Square:
## Estimate
## Zalc 0.027
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## Zalc ~
## sex1 (.p1.) 0.239 0.026 9.304 0.000 0.189 0.290
## SESscor (.p2.) 0.096 0.016 6.183 0.000 0.066 0.127
## Zgcse (.p3.) -0.005 0.017 -0.283 0.777 -0.038 0.029
## Zhqual (.p4.) 0.042 0.016 2.594 0.009 0.010 0.073
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## sex1 ~~
## SESscore 0.014 0.006 2.426 0.015 0.003 0.026
## Zgcse -0.026 0.006 -4.232 0.000 -0.038 -0.014
## Zhqual -0.021 0.008 -2.594 0.009 -0.036 -0.005
## SESscore ~~
## Zgcse 0.447 0.013 34.437 0.000 0.422 0.473
## Zhqual 0.342 0.015 22.277 0.000 0.312 0.372
## Zgcse ~~
## Zhqual 0.565 0.018 31.536 0.000 0.529 0.600
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc (.16.) -0.097 0.016 -6.042 0.000 -0.129 -0.066
## sex1 0.474 0.006 76.503 0.000 0.462 0.486
## SESscor -0.034 0.012 -2.922 0.003 -0.057 -0.011
## Zgcse 0.000 0.012 0.000 1.000 -0.024 0.024
## Zhqual -0.121 0.016 -7.500 0.000 -0.152 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .Zalc 0.978 0.025 39.776 0.000 0.930 1.026
## sex1 0.249 0.004 56.956 0.000 0.241 0.258
## SESscore 0.875 0.016 56.315 0.000 0.844 0.905
## Zgcse 1.000 0.018 56.956 0.000 0.965 1.034
## Zhqual 1.039 0.024 42.584 0.000 0.991 1.087
##
## R-Square:
## Estimate
## Zalc 0.026
lavTestLRT(multi.alc.free, multi.alc.cons)
##
## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff RMSEA Df diff Pr(>Chisq)
## multi.alc.free 0 122688 122987 0.0000
## multi.alc.cons 5 122686 122947 7.2337 7.2337 0.0082964 5 0.2038
#Logistic and multinomial multi-group regression models
model3.benf <- 'u1cbenf11 ~ sex1 + SESscore + Zgcse + Zhqual'
multi.benf.free <- sem(model3.benf, data = df, group = "random", ordered = c("u1cbenf11"), missing = "listwise")
summary(multi.benf.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 41 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations per group: Used Total
## 0 3650 6493
## 1 3628 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
## Test statistic for each group:
## 0 0.000 0.000
## 1 0.000 0.000
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.173 0.086 -2.011 0.044 -0.342 -0.004
## SESscore -0.152 0.049 -3.086 0.002 -0.248 -0.055
## Zgcse -0.151 0.045 -3.329 0.001 -0.240 -0.062
## Zhqual -0.142 0.038 -3.771 0.000 -0.216 -0.068
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.747 0.054 32.236 0.000 1.641 1.854
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.111
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 -0.178 0.080 -2.235 0.025 -0.335 -0.022
## SESscore -0.119 0.044 -2.683 0.007 -0.206 -0.032
## Zgcse -0.107 0.048 -2.224 0.026 -0.201 -0.013
## Zhqual -0.204 0.037 -5.571 0.000 -0.275 -0.132
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11|t1 1.688 0.050 33.832 0.000 1.590 1.785
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.106
multi.benf.cons <- sem(model3.benf, data = df, group = "random", group.equal = c("intercepts", "regressions"), ordered = c("u1cbenf11"), missing = "listwise")
summary(multi.benf.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 29 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 11
## Number of equality constraints 5
##
## Number of observations per group: Used Total
## 0 3650 6493
## 1 3628 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 2.202 2.328
## Degrees of freedom 4 4
## P-value (Chi-square) 0.699 0.676
## Scaling correction factor 1.072
## Shift parameter 0.274
## simple second-order correction
## Test statistic for each group:
## 0 1.091 1.155
## 1 1.111 1.173
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.019 0.019
## P-value H_0: RMSEA <= 0.050 1.000 1.000
## P-value H_0: RMSEA >= 0.080 0.000 0.000
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 (.p1.) -0.179 0.060 -3.004 0.003 -0.295 -0.062
## SESscor (.p2.) -0.136 0.034 -4.025 0.000 -0.203 -0.070
## Zgcse (.p3.) -0.132 0.034 -3.940 0.000 -0.198 -0.067
## Zhqual (.p4.) -0.176 0.027 -6.556 0.000 -0.229 -0.123
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1c11|1 (.p5.) 1.744 0.054 32.390 0.000 1.638 1.849
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 1.000 1.000 1.000
##
## R-Square:
## Estimate
## u1cbenf11 0.112
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 ~
## sex1 (.p1.) -0.179 0.060 -3.004 0.003 -0.295 -0.062
## SESscor (.p2.) -0.136 0.034 -4.025 0.000 -0.203 -0.070
## Zgcse (.p3.) -0.132 0.034 -3.940 0.000 -0.198 -0.067
## Zhqual (.p4.) -0.176 0.027 -6.556 0.000 -0.229 -0.123
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1c11|1 (.p5.) 1.744 0.054 32.390 0.000 1.638 1.849
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .u1cbenf11 1.063 1.063 1.063
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## u1cbenf11 0.970 0.041 23.716 0.000 0.890 1.050
##
## R-Square:
## Estimate
## u1cbenf11 0.104
lavTestLRT(multi.benf.free, multi.benf.cons)
##
## Scaled Chi-Squared Difference Test (method = "satorra.2000")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## multi.benf.free 0 0.000
## multi.benf.cons 4 2.202 2.3281 4 0.6757
model3.status_bin <- 'status_bin ~ sex1 + SESscore + Zgcse + Zhqual'
multi.status_bin.free <- sem(model3.status_bin, data = df, group = "random", ordered = c("status_bin"), missing = "listwise")
summary(multi.status_bin.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 30 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
## Test statistic for each group:
## 0 0.000 0.000
## 1 0.000 0.000
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.047 0.059 -0.792 0.428 -0.162 0.069
## SESscore -0.057 0.035 -1.608 0.108 -0.126 0.012
## Zgcse -0.038 0.038 -0.991 0.322 -0.113 0.037
## Zhqual 0.056 0.033 1.686 0.092 -0.009 0.120
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.317 0.037 -35.756 0.000 -1.389 -1.245
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.005
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 -0.008 0.058 -0.142 0.887 -0.122 0.105
## SESscore -0.069 0.035 -1.984 0.047 -0.138 -0.001
## Zgcse -0.039 0.037 -1.051 0.293 -0.112 0.034
## Zhqual 0.100 0.033 3.030 0.002 0.035 0.165
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin|t1 -1.284 0.037 -34.269 0.000 -1.357 -1.210
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.009
multi.status_bin.cons <- sem(model3.status_bin, data = df, group = "random", group.equal = c("intercepts", "regressions"), ordered = c("status_bin"), missing = "listwise")
summary(multi.status_bin.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 11
## Number of equality constraints 5
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1.268 1.505
## Degrees of freedom 4 4
## P-value (Chi-square) 0.867 0.826
## Scaling correction factor 1.075
## Shift parameter 0.325
## simple second-order correction
## Test statistic for each group:
## 0 0.622 0.741
## 1 0.646 0.763
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.013 0.015
## P-value H_0: RMSEA <= 0.050 1.000 1.000
## P-value H_0: RMSEA >= 0.080 0.000 0.000
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 (.p1.) -0.028 0.042 -0.663 0.508 -0.109 0.054
## SESscor (.p2.) -0.064 0.025 -2.538 0.011 -0.113 -0.015
## Zgcse (.p3.) -0.039 0.027 -1.444 0.149 -0.092 0.014
## Zhqual (.p4.) 0.078 0.024 3.327 0.001 0.032 0.125
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## stts_|1 (.p5.) -1.315 0.037 -35.448 0.000 -1.388 -1.243
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 1.000 1.000 1.000
##
## R-Square:
## Estimate
## status_bin 0.007
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin ~
## sex1 (.p1.) -0.028 0.042 -0.663 0.508 -0.109 0.054
## SESscor (.p2.) -0.064 0.025 -2.538 0.011 -0.113 -0.015
## Zgcse (.p3.) -0.039 0.027 -1.444 0.149 -0.092 0.014
## Zhqual (.p4.) 0.078 0.024 3.327 0.001 0.032 0.125
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## stts_|1 (.p5.) -1.315 0.037 -35.448 0.000 -1.388 -1.243
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .status_bin 1.047 1.047 1.047
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## status_bin 0.977 0.040 24.263 0.000 0.898 1.056
##
## R-Square:
## Estimate
## status_bin 0.007
lavTestLRT(multi.status_bin.free, multi.status_bin.cons)
##
## Scaled Chi-Squared Difference Test (method = "satorra.2000")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## multi.status_bin.free 0 0.0000
## multi.status_bin.cons 4 1.2684 1.5047 4 0.8258
##first, create dummy variables for status again now in dataset with both twins that is used here for the multi-group analyses
#dummy code status variable
#specify status as factor, create 4 dummy variables for originally 5 categories (unemployed is always set as the reference category), and bind new variables to df
df$status1 = as.factor(df$status1)
st_working <- ifelse(df$status1 == '1', 1, 0)
st_studying <- ifelse(df$status1 == '2', 1, 0)
st_parent <- ifelse(df$status1 == '3', 1, 0)
st_gapyear <- ifelse(df$status1 == '4', 1, 0)
df_dummy = cbind(df, st_working, st_studying, st_parent, st_gapyear)
write.csv(df_dummy, '/Users/cgb538/Library/CloudStorage/GoogleDrive-alexandra.starr@york.ac.uk/My Drive/projects and papers/DevPsych_prediction grades adulthood/data/grades_adulth_prepared_bothtwins_dummy.csv', row.names = F, na = 'NA')
#employment status: working vs. unemployed
model3.st_working <- 'st_working ~ sex1 + SESscore + Zgcse + Zhqual'
multi.st_working.free <- sem(model3.st_working, data = df_dummy, group = "random", ordered = c("st_working"), missing = "listwise")
summary(multi.st_working.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
## Test statistic for each group:
## 0 0.000 0.000
## 1 0.000 0.000
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.046 0.045 -1.012 0.312 -0.134 0.043
## SESscore -0.104 0.027 -3.852 0.000 -0.156 -0.051
## Zgcse -0.129 0.029 -4.374 0.000 -0.187 -0.071
## Zhqual -0.381 0.025 -15.254 0.000 -0.430 -0.332
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.132 0.028 -4.743 0.000 -0.186 -0.077
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.204
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 -0.122 0.045 -2.720 0.007 -0.209 -0.034
## SESscore -0.141 0.026 -5.392 0.000 -0.192 -0.090
## Zgcse -0.112 0.029 -3.923 0.000 -0.168 -0.056
## Zhqual -0.361 0.025 -14.477 0.000 -0.410 -0.312
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working|t1 -0.123 0.028 -4.413 0.000 -0.178 -0.069
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.198
multi.st_working.cons <- sem(model3.st_working, data = df_dummy, group = "random", group.equal = c("intercepts", "regressions"), ordered = c("st_working"), missing = "listwise")
summary(multi.st_working.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 28 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 11
## Number of equality constraints 5
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 2.880 2.796
## Degrees of freedom 4 4
## P-value (Chi-square) 0.578 0.592
## Scaling correction factor 1.189
## Shift parameter 0.373
## simple second-order correction
## Test statistic for each group:
## 0 1.435 1.394
## 1 1.445 1.402
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.022 0.021
## P-value H_0: RMSEA <= 0.050 1.000 1.000
## P-value H_0: RMSEA >= 0.080 0.000 0.000
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 (.p1.) -0.084 0.032 -2.622 0.009 -0.147 -0.021
## SESscor (.p2.) -0.124 0.019 -6.380 0.000 -0.162 -0.086
## Zgcse (.p3.) -0.122 0.021 -5.720 0.000 -0.163 -0.080
## Zhqual (.p4.) -0.375 0.022 -17.050 0.000 -0.418 -0.332
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_wr|1 (.p5.) -0.129 0.020 -6.318 0.000 -0.169 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_working 0.205
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working ~
## sex1 (.p1.) -0.084 0.032 -2.622 0.009 -0.147 -0.021
## SESscor (.p2.) -0.124 0.019 -6.380 0.000 -0.162 -0.086
## Zgcse (.p3.) -0.122 0.021 -5.720 0.000 -0.163 -0.080
## Zhqual (.p4.) -0.375 0.022 -17.050 0.000 -0.418 -0.332
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_wr|1 (.p5.) -0.129 0.020 -6.318 0.000 -0.169 -0.089
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_working 1.041 1.041 1.041
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_working 0.980 0.068 14.357 0.000 0.846 1.114
##
## R-Square:
## Estimate
## st_working 0.196
lavTestLRT(multi.st_working.free, multi.st_working.cons)
##
## Scaled Chi-Squared Difference Test (method = "satorra.2000")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## multi.st_working.free 0 0.0000
## multi.st_working.cons 4 2.8802 2.7962 4 0.5925
#employment status: studying/apprenticeship vs. unemployed
model3.st_studying <- 'st_studying ~ sex1 + SESscore + Zgcse + Zhqual'
multi.st_studying.free <- sem(model3.st_studying, data = df_dummy, group = "random", ordered = c("st_studying"), missing = "listwise")
summary(multi.st_studying.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 23 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
## Test statistic for each group:
## 0 0.000 0.000
## 1 0.000 0.000
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.025 0.046 0.552 0.581 -0.065 0.116
## SESscore 0.082 0.027 2.997 0.003 0.028 0.135
## Zgcse 0.116 0.031 3.750 0.000 0.055 0.177
## Zhqual 0.515 0.028 18.449 0.000 0.461 0.570
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.433 0.030 14.628 0.000 0.375 0.491
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.274
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 0.137 0.046 2.983 0.003 0.047 0.227
## SESscore 0.111 0.027 4.177 0.000 0.059 0.163
## Zgcse 0.101 0.030 3.416 0.001 0.043 0.159
## Zhqual 0.528 0.028 18.883 0.000 0.473 0.582
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying|t1 0.454 0.030 15.102 0.000 0.395 0.513
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.286
multi.st_studying.cons <- sem(model3.st_studying, data = df_dummy, group = "random", group.equal = c("intercepts", "regressions"), ordered = c("st_studying"), missing = "listwise")
summary(multi.st_studying.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 26 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 11
## Number of equality constraints 5
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 3.476 3.525
## Degrees of freedom 4 4
## P-value (Chi-square) 0.482 0.474
## Scaling correction factor 1.119
## Shift parameter 0.419
## simple second-order correction
## Test statistic for each group:
## 0 1.827 1.842
## 1 1.649 1.683
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.024 0.024
## P-value H_0: RMSEA <= 0.050 1.000 1.000
## P-value H_0: RMSEA >= 0.080 0.000 0.000
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 (.p1.) 0.081 0.032 2.539 0.011 0.018 0.143
## SESscor (.p2.) 0.095 0.019 5.018 0.000 0.058 0.132
## Zgcse (.p3.) 0.106 0.021 4.968 0.000 0.064 0.147
## Zhqual (.p4.) 0.510 0.025 20.818 0.000 0.462 0.558
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_st|1 (.p5.) 0.434 0.024 17.960 0.000 0.387 0.482
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_studying 0.271
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying ~
## sex1 (.p1.) 0.081 0.032 2.539 0.011 0.018 0.143
## SESscor (.p2.) 0.095 0.019 5.018 0.000 0.058 0.132
## Zgcse (.p3.) 0.106 0.021 4.968 0.000 0.064 0.147
## Zhqual (.p4.) 0.510 0.025 20.818 0.000 0.462 0.558
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_st|1 (.p5.) 0.434 0.024 17.960 0.000 0.387 0.482
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_studying 0.919 0.919 0.919
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_studying 1.043 0.060 17.355 0.000 0.925 1.161
##
## R-Square:
## Estimate
## st_studying 0.287
lavTestLRT(multi.st_studying.free, multi.st_studying.cons)
##
## Scaled Chi-Squared Difference Test (method = "satorra.2000")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## multi.st_studying.free 0 0.000
## multi.st_studying.cons 4 3.476 3.5246 4 0.4741
#employment status: full-time parent vs. unemployed
model3.st_parent <- 'st_parent ~ sex1 + SESscore + Zgcse + Zhqual'
multi.st_parent.free <- sem(model3.st_parent, data = df_dummy, group = "random", ordered = c("st_parent"), missing = "listwise")
summary(multi.st_parent.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 57 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
## Test statistic for each group:
## 0 0.000 0.000
## 1 0.000 0.000
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.853 0.250 -3.415 0.001 -1.343 -0.364
## SESscore -0.250 0.110 -2.275 0.023 -0.465 -0.035
## Zgcse -0.206 0.090 -2.282 0.023 -0.383 -0.029
## Zhqual -0.297 0.084 -3.547 0.000 -0.461 -0.133
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.624 0.171 15.307 0.000 2.288 2.960
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.338
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 -0.553 0.302 -1.831 0.067 -1.146 0.039
## SESscore -0.312 0.125 -2.494 0.013 -0.556 -0.067
## Zgcse -0.080 0.109 -0.728 0.466 -0.294 0.135
## Zhqual -0.390 0.132 -2.960 0.003 -0.649 -0.132
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent|t1 2.850 0.230 12.403 0.000 2.400 3.300
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.310
multi.st_parent.cons <- sem(model3.st_parent, data = df_dummy, group = "random", group.equal = c("intercepts", "regressions"), ordered = c("st_parent"), missing = "listwise")
summary(multi.st_parent.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 43 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 11
## Number of equality constraints 5
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 2.018 2.383
## Degrees of freedom 4 4
## P-value (Chi-square) 0.732 0.666
## Scaling correction factor 1.133
## Shift parameter 0.601
## simple second-order correction
## Test statistic for each group:
## 0 0.862 1.062
## 1 1.157 1.321
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.018 0.020
## P-value H_0: RMSEA <= 0.050 1.000 1.000
## P-value H_0: RMSEA >= 0.080 0.000 0.000
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 (.p1.) -0.705 0.196 -3.593 0.000 -1.090 -0.321
## SESscor (.p2.) -0.269 0.083 -3.224 0.001 -0.433 -0.106
## Zgcse (.p3.) -0.148 0.069 -2.157 0.031 -0.283 -0.014
## Zhqual (.p4.) -0.318 0.071 -4.508 0.000 -0.457 -0.180
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_pr|1 (.p5.) 2.639 0.176 14.961 0.000 2.293 2.984
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_parent 0.307
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent ~
## sex1 (.p1.) -0.705 0.196 -3.593 0.000 -1.090 -0.321
## SESscor (.p2.) -0.269 0.083 -3.224 0.001 -0.433 -0.106
## Zgcse (.p3.) -0.148 0.069 -2.157 0.031 -0.283 -0.014
## Zhqual (.p4.) -0.318 0.071 -4.508 0.000 -0.457 -0.180
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_pr|1 (.p5.) 2.639 0.176 14.961 0.000 2.293 2.984
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_parent 0.872 0.872 0.872
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_parent 1.071 0.112 9.529 0.000 0.850 1.291
##
## R-Square:
## Estimate
## st_parent 0.336
lavTestLRT(multi.st_parent.free, multi.st_parent.cons)
##
## Scaled Chi-Squared Difference Test (method = "satorra.2000")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## multi.st_parent.free 0 0.0000
## multi.st_parent.cons 4 2.0184 2.3825 4 0.6658
#employment status: gap year/travelling vs. unemployed
model3.st_gapyear <- 'st_gapyear ~ sex1 + SESscore + Zgcse + Zhqual'
multi.st_gapyear.free <- sem(model3.st_gapyear, data = df_dummy, group = "random", ordered = c("st_gapyear"), missing = "listwise")
summary(multi.st_gapyear.free, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 33 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 10
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
## Test statistic for each group:
## 0 0.000 0.000
## 1 0.000 0.000
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.000 0.000
## P-value H_0: RMSEA <= 0.050 NA NA
## P-value H_0: RMSEA >= 0.080 NA NA
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 0.037 0.087 0.422 0.673 -0.134 0.208
## SESscore 0.150 0.052 2.877 0.004 0.048 0.252
## Zgcse 0.094 0.059 1.602 0.109 -0.021 0.209
## Zhqual 0.012 0.057 0.213 0.831 -0.100 0.124
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.946 0.056 34.568 0.000 1.836 2.057
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.041
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 -0.113 0.083 -1.357 0.175 -0.276 0.050
## SESscore 0.137 0.050 2.741 0.006 0.039 0.235
## Zgcse 0.056 0.056 1.003 0.316 -0.054 0.167
## Zhqual -0.015 0.055 -0.268 0.789 -0.123 0.093
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear|t1 1.805 0.053 33.897 0.000 1.701 1.910
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.025
multi.st_gapyear.cons <- sem(model3.st_gapyear, data = df_dummy, group = "random", group.equal = c("intercepts", "regressions"), ordered = c("st_gapyear"), missing = "listwise")
summary(multi.st_gapyear.cons, fit.measures = TRUE, ci = TRUE, rsquare = TRUE)
## lavaan 0.6.15 ended normally after 27 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 11
## Number of equality constraints 5
##
## Number of observations per group: Used Total
## 0 3653 6493
## 1 3635 6488
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1.878 2.032
## Degrees of freedom 4 4
## P-value (Chi-square) 0.758 0.730
## Scaling correction factor 1.072
## Shift parameter 0.280
## simple second-order correction
## Test statistic for each group:
## 0 0.912 0.991
## 1 0.966 1.041
##
## Model Test Baseline Model:
##
## Test statistic 0.000 0.000
## Degrees of freedom 0 0
## P-value NA NA
## Scaling correction factor NA
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000 1.000
## Tucker-Lewis Index (TLI) 1.000 1.000
##
## Robust Comparative Fit Index (CFI) NA
## Robust Tucker-Lewis Index (TLI) NA
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000 0.000
## 90 Percent confidence interval - lower 0.000 0.000
## 90 Percent confidence interval - upper 0.017 0.018
## P-value H_0: RMSEA <= 0.050 1.000 1.000
## P-value H_0: RMSEA >= 0.080 0.000 0.000
##
## Robust RMSEA NA
## 90 Percent confidence interval - lower NA
## 90 Percent confidence interval - upper NA
## P-value H_0: Robust RMSEA <= 0.050 NA
## P-value H_0: Robust RMSEA >= 0.080 NA
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.000 0.000
##
## Parameter Estimates:
##
## Standard errors Robust.sem
## Information Expected
## Information saturated (h1) model Unstructured
##
##
## Group 1 [0]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 (.p1.) -0.040 0.063 -0.643 0.520 -0.163 0.083
## SESscor (.p2.) 0.149 0.038 3.966 0.000 0.075 0.223
## Zgcse (.p3.) 0.078 0.042 1.849 0.064 -0.005 0.161
## Zhqual (.p4.) -0.001 0.041 -0.032 0.975 -0.082 0.079
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gp|1 (.p5.) 1.946 0.056 34.569 0.000 1.836 2.057
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.000 1.000 1.000
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 1.000 1.000 1.000
##
## R-Square:
## Estimate
## st_gapyear 0.033
##
##
## Group 2 [1]:
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear ~
## sex1 (.p1.) -0.040 0.063 -0.643 0.520 -0.163 0.083
## SESscor (.p2.) 0.149 0.038 3.966 0.000 0.075 0.223
## Zgcse (.p3.) 0.078 0.042 1.849 0.064 -0.005 0.161
## Zhqual (.p4.) -0.001 0.041 -0.032 0.975 -0.082 0.079
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 0.000 0.000 0.000
##
## Thresholds:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gp|1 (.p5.) 1.946 0.056 34.569 0.000 1.836 2.057
##
## Variances:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## .st_gapyear 1.162 1.162 1.162
##
## Scales y*:
## Estimate Std.Err z-value P(>|z|) ci.lower ci.upper
## st_gapyear 0.928 0.038 24.152 0.000 0.852 1.003
##
## R-Square:
## Estimate
## st_gapyear 0.028
lavTestLRT(multi.st_gapyear.free, multi.st_gapyear.cons)
##
## Scaled Chi-Squared Difference Test (method = "satorra.2000")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## multi.st_gapyear.free 0 0.0000
## multi.st_gapyear.cons 4 1.8782 2.0323 4 0.7298