Homework 8 Stats 2
Joshua Reyna
3/29/2021
library(car)## Loading required package: carDatalibrary(mice)##
## Attaching package: 'mice'## The following object is masked from 'package:stats':
##
## filter## The following objects are masked from 'package:base':
##
## cbind, rbindlibrary(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:car':
##
## recode## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(haven)
NSDUH_2019 <- read_sav("NSDUH_2019.SAV")
View(NSDUH_2019)nams<-names(NSDUH_2019)
head(nams, n=10)## [1] "QUESTID2" "FILEDATE" "CIGEVER" "CIGOFRSM" "CIGWILYR" "CIGTRY"
## [7] "CIGYFU" "CIGMFU" "CIGREC" "CIG30USE"newnames<-tolower(gsub(pattern = "_",replacement = "",x = nams))
names(NSDUH_2019)<-newnamesNSDUH_2019$attempt_suicide<-Recode(NSDUH_2019$adwrsatp, recodes="1=1; 2=0;else=NA")
## Main variable hopeless last thirty days
NSDUH_2019$hopelesslst30days<-Recode(NSDUH_2019$dsthop30,
recodes="1:2=3;3:4=2;5=1; else=NA")
NSDUH_2019$fltnervouslst30days<-Recode(NSDUH_2019$dstnrv30,
recodes="1:2=3;3:4=2;5=1; else=NA")
NSDUH_2019$fltrestlesslst30days<-Recode(NSDUH_2019$dstrst30,
recodes="1:2=3;3:4=2;5=1; else=NA")
NSDUH_2019$fltsadlst30days<-Recode(NSDUH_2019$dstchr30,
recodes="1:2=3;3:4=2;5=1; else=NA")
NSDUH_2019$effortlst30days<-Recode(NSDUH_2019$dsteff30,
recodes="1:2=3;3:4=2;5=1; else=NA")
NSDUH_2019$fltdwnlst30days<-Recode(NSDUH_2019$dstngd30,
recodes="1:2=3;3:4=2;5=1; else=NA")
## marital status
NSDUH_2019$marst<-Recode(NSDUH_2019$irmarit, recodes="1='married'; 2='divorced'; 3='widowed'; 4='separated'; else=NA", as.factor=T)
NSDUH_2019$marst<-relevel(NSDUH_2019$marst, ref='married')
## education recodes
NSDUH_2019$educ<-Recode(NSDUH_2019$ireduhighst2, recodes="1:7='LssThnHgh'; 8='highschool'; 9='someCollege'; 10='associates'; 11='colgrad';else=NA", as.factor=T)
NSDUH_2019$educ<-relevel(NSDUH_2019$educ, ref='colgrad')
## sexuality recodes
NSDUH_2019$sexuality<-Recode(NSDUH_2019$sexident, recodes="1='Heterosexual'; 2='Les/Gay'; 3='Bisexual';else=NA", as.factor=T)
NSDUH_2019$sexuality<-relevel(NSDUH_2019$sexuality, ref='Heterosexual')
## gender recodes
NSDUH_2019$male<-as.factor(ifelse(NSDUH_2019$irsex==1, "Male", "Female"))
## Race recoded items
NSDUH_2019$black<-Recode(NSDUH_2019$newrace2, recodes="2=1; 9=NA; else=0")
NSDUH_2019$white<-Recode(NSDUH_2019$newrace2, recodes="1=1; 9=NA; else=0")
NSDUH_2019$other<-Recode(NSDUH_2019$newrace2, recodes="3:4=1; 9=NA; else=0")
NSDUH_2019$mult_race<-Recode(NSDUH_2019$newrace2, recodes="6=1; 9=NA; else=0")
NSDUH_2019$asian<-Recode(NSDUH_2019$newrace2, recodes="5=1; 9=NA; else=0")
NSDUH_2019$hispanic<-Recode(NSDUH_2019$newrace2, recodes="7=1; 9=NA; else=0")
NSDUH_2019$race_eth<-Recode(NSDUH_2019$newrace2,
recodes="1='white'; 2='black'; 3='other'; 4='asian'; 5='mult_race'; 6='hispanic'; else=NA",
as.factor = T)
NSDUH_2019$race_eth<-relevel(NSDUH_2019$race_eth, ref='white')
NSDUH_2019$lst_alc_use2<-Recode(NSDUH_2019$iralcrc, recodes="1='last 30days'; 2='12>1month'; 3='>12months'; else=NA", as.factor=T)
NSDUH_2019$dep_year2<-Recode(NSDUH_2019$amdeyr, recodes="1=1; 2=0;else=NA")
NSDUH_2019$age_cat<-Recode(NSDUH_2019$age2, recodes="7:8='18-19'; 9:10='20-21'; 11='22-23'; 12='24-25'; 13='26-29'; 14='30-34'; 15='35-49'; 16='50-64'; 17='65+'; else=NA", as.factor=T)
NSDUH_2019$daysalc<-Recode(NSDUH_2019$alcdays, recodes = "85=NA; 91=NA; 93=NA; 94=NA; 97=NA; 98=NA ")
NSDUH_2019$weekhrswrkd<-Recode(NSDUH_2019$wrkdhrswk2, recodes = "985=NA; 994=NA; 997=NA; 998=NA; 999=NA")Missing Values outcome if had last alcholic drink in 30 days, with predictors wrkdhrswk2 sexuality, race_eth , marst, educ
summary(NSDUH_2019[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd", "marst", "dep_year2")])## daysalc sexuality race_eth weekhrswrkd
## Min. : 1.000 Heterosexual:38214 white :32089 Min. : 1.00
## 1st Qu.: 2.000 Bisexual : 2642 asian : 292 1st Qu.:30.00
## Median : 4.000 Les/Gay : 976 black : 7256 Median :40.00
## Mean : 7.499 NA's :14304 hispanic : 2202 Mean :36.47
## 3rd Qu.:10.000 mult_race: 2697 3rd Qu.:45.00
## Max. :30.000 other : 752 Max. :61.00
## NA's :31467 NA's :10848 NA's :28467
## marst dep_year2
## married :16983 Min. :0.000
## divorced : 1333 1st Qu.:0.000
## separated:26750 Median :0.000
## widowed : 4515 Mean :0.106
## NA's : 6555 3rd Qu.:0.000
## Max. :1.000
## NA's :13954#Report the pattern of missingness among all of these variables # The results of the summary analysis indicates a rather large amount of missing data. The main outcome variable actually has an rather large amount of missing variables. The NSDUH_2019 has about 56136 observations in its variables. Of that the outcome variable is missing 31,467. This is followed closely by hours worked in a week, which according to the codebook indicates over 27,000 of which came from a legitimate skip. Race ethnicity, depressive episodes in the year, and sexuality as well had rather large amounts of missing data. With marital status having the least out of the missing variables. Which again coming from the codebook comes from legitimate skips. It is possible that a majority of the missing data in comes from this type of factor. But its rather curious why race/ethnicity is missing such high of values. Depressive epsiodes was dropped due to not being a categorical variable.
Perform a mean (a mean for numeric data) or a modal imputation (for categorical data) of all values.
Mean Imputation. The mean imputation reveals that on average 7.4 days of alcohol were used to complete the missing values, with 35.47 hours worked during the week.
summary(NSDUH_2019$daysalc) ## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.000 2.000 4.000 7.499 10.000 30.000 31467summary(NSDUH_2019$weekhrswrkd) ## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.00 30.00 40.00 36.47 45.00 61.00 28467NSDUH_2019$daysalc.imp.mean<-ifelse(is.na(NSDUH_2019$daysalc)==T, mean(NSDUH_2019$daysalc, na.rm=T), NSDUH_2019$daysalc)
NSDUH_2019$weekhrswrkd.imp.mean<-ifelse(is.na(NSDUH_2019$weekhrswrkd)==T, mean(NSDUH_2019$weekhrswrkd, na.rm=T), NSDUH_2019$weekhrswrkd)
mean(NSDUH_2019$daysalc.imp.mean, na.rm=T)## [1] 7.498804mean(NSDUH_2019$weekhrswrkd.imp.mean, na.rm=T)## [1] 36.465Modal Imputation. The modal imputation reveals that the most missing category for these types of variables for sexuality was heterosexuals, whites for racial, and separated for marital status.
mcv.sexuality<-factor(names(which.max(table(NSDUH_2019$sexuality))), levels=levels(NSDUH_2019$sexuality))
mcv.sexuality## [1] Heterosexual
## Levels: Heterosexual Bisexual Les/Gaymcv.race_eth<-factor(names(which.max(table(NSDUH_2019$race_eth))), levels=levels(NSDUH_2019$race_eth))
mcv.race_eth## [1] white
## Levels: white asian black hispanic mult_race othermcv.marst<-factor(names(which.max(table(NSDUH_2019$marst))), levels=levels(NSDUH_2019$marst))
mcv.marst## [1] separated
## Levels: married divorced separated widowedNSDUH_2019$sexuality.imp<-as.factor(ifelse(is.na(NSDUH_2019$sexuality)==T, mcv.sexuality, NSDUH_2019$sexuality))
levels(NSDUH_2019$sexuality.imp)<-levels(NSDUH_2019$sexuality)
NSDUH_2019$race_eth.imp<-as.factor(ifelse(is.na(NSDUH_2019$race_eth)==T, mcv.race_eth, NSDUH_2019$race_eth))
levels(NSDUH_2019$race_eth.imp)<-levels(NSDUH_2019$race_eth)
NSDUH_2019$marst.imp<-as.factor(ifelse(is.na(NSDUH_2019$marst)==T, mcv.marst, NSDUH_2019$marst))
levels(NSDUH_2019$marst.imp)<-levels(NSDUH_2019$marst)prop.table(table(NSDUH_2019$sexuality))##
## Heterosexual Bisexual Les/Gay
## 0.91351119 0.06315739 0.02333142prop.table(table(NSDUH_2019$race_eth))##
## white asian black hispanic mult_race other
## 0.708554142 0.006447624 0.160219043 0.048622152 0.059552199 0.016604840prop.table(table(NSDUH_2019$marst))##
## married divorced separated widowed
## 0.34253040 0.02688530 0.53952119 0.09106311prop.table(table(NSDUH_2019$sexuality.imp))##
## Heterosexual Bisexual Les/Gay
## 0.93554938 0.04706427 0.01738635prop.table(table(NSDUH_2019$race_eth.imp))##
## white asian black hispanic mult_race other
## 0.764874590 0.005201653 0.129257517 0.039226165 0.048044036 0.013396038prop.table(table(NSDUH_2019$marst.imp))##
## married divorced separated widowed
## 0.30253313 0.02374590 0.59329129 0.08042967In terms of proportions following the imputed vs non imputed variables, the racial categories specifically the whites grew the moest proportion wise. This increase from 0.70855 to 0.76487. Interestingly most of the other racial category changes occured at the third decimal point. The changes then in greatest magnitude lie with marital status, followed by sexuality. Again they are reflective of the modals imputation so separated, then heteosexuals receive the greatest increases. Weirdly, these are the reference categories.
barplot(prop.table(table(NSDUH_2019$sexuality)), main="Original Data", ylim=c(0, .6))
barplot(prop.table(table(NSDUH_2019$race_eth)), main="Original Data", ylim=c(0, .6))
barplot(prop.table(table(NSDUH_2019$marst)), main="Original Data", ylim=c(0, .6))
barplot(prop.table(table(NSDUH_2019$sexuality.imp)), main="Imputed Data",ylim=c(0, .6))
barplot(prop.table(table(NSDUH_2019$race_eth.imp)), main="Imputed Data",ylim=c(0, .6))
barplot(prop.table(table(NSDUH_2019$marst.imp)), main="Imputed Data",ylim=c(0, .6))
##Perform the analysis using this imputed data. What are your results? According to the results, with the imputed values more hours worked in a week leads to an increase in alchol consumed during the month. With both being divorced and widowed increasing the consumption of alcohol within the last month, however beign separated decreases the amount consumed. Lesbians and gays compared to their heteroseuxal counterparts consume more alchol during the month. Blacks and multi racial individuals consume less alchol during the month than their white counterparts.
fit1<-lm(daysalc.imp.mean~weekhrswrkd.imp.mean+marst.imp+sexuality.imp+race_eth.imp, data=NSDUH_2019)
summary(fit1)##
## Call:
## lm(formula = daysalc.imp.mean ~ weekhrswrkd.imp.mean + marst.imp +
## sexuality.imp + race_eth.imp, data = NSDUH_2019)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.9744 -2.3578 0.1252 0.4481 23.6594
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.067635 0.093612 75.499 < 2e-16 ***
## weekhrswrkd.imp.mean 0.021990 0.002192 10.031 < 2e-16 ***
## marst.impdivorced 0.565434 0.143205 3.948 7.88e-05 ***
## marst.impseparated -0.522741 0.048585 -10.759 < 2e-16 ***
## marst.impwidowed 0.234434 0.084421 2.777 0.00549 **
## sexuality.impBisexual 0.026877 0.100472 0.268 0.78908
## sexuality.impLes/Gay 0.484268 0.162586 2.979 0.00290 **
## race_eth.impasian -0.307911 0.295196 -1.043 0.29692
## race_eth.impblack -0.468150 0.064271 -7.284 3.28e-13 ***
## race_eth.imphispanic -0.064021 0.110175 -0.581 0.56119
## race_eth.impmult_race -0.737357 0.099926 -7.379 1.62e-13 ***
## race_eth.impother -0.184120 0.185001 -0.995 0.31962
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.027 on 56124 degrees of freedom
## Multiple R-squared: 0.008658, Adjusted R-squared: 0.008464
## F-statistic: 44.56 on 11 and 56124 DF, p-value: < 2.2e-16md.pattern(NSDUH_2019[,c("daysalc", "sexuality", "race_eth", "weekhrswrkd", "marst", "dep_year2")])
## marst race_eth dep_year2 sexuality weekhrswrkd daysalc
## 13954 1 1 1 1 1 1 0
## 7482 1 1 1 1 1 0 1
## 5618 1 1 1 1 0 1 1
## 7106 1 1 1 1 0 0 2
## 84 1 1 1 0 1 1 1
## 100 1 1 1 0 1 0 2
## 77 1 1 1 0 0 1 2
## 231 1 1 1 0 0 0 3
## 58 1 1 0 1 1 1 1
## 49 1 1 0 1 1 0 2
## 62 1 1 0 1 0 1 2
## 100 1 1 0 1 0 0 3
## 303 1 1 0 0 1 1 2
## 983 1 1 0 0 1 0 3
## 547 1 1 0 0 0 1 3
## 3565 1 1 0 0 0 0 4
## 2416 1 0 1 1 1 1 1
## 1851 1 0 1 1 1 0 2
## 1109 1 0 1 1 0 1 2
## 1955 1 0 1 1 0 0 3
## 15 1 0 1 0 1 1 2
## 42 1 0 1 0 1 0 3
## 19 1 0 1 0 0 1 3
## 123 1 0 1 0 0 0 4
## 12 1 0 0 1 1 1 2
## 17 1 0 0 1 1 0 3
## 17 1 0 0 1 0 1 3
## 26 1 0 0 1 0 0 4
## 65 1 0 0 0 1 1 3
## 238 1 0 0 0 1 0 4
## 158 1 0 0 0 0 1 4
## 1199 1 0 0 0 0 0 5
## 116 0 1 0 0 0 1 4
## 4853 0 1 0 0 0 0 5
## 39 0 0 0 0 0 1 5
## 1547 0 0 0 0 0 0 6
## 6555 10848 13954 14304 28467 31467 105595md.pairs(NSDUH_2019[,c("daysalc", "sexuality", "race_eth", "weekhrswrkd", "marst", "dep_year2")])## $rr
## daysalc sexuality race_eth weekhrswrkd marst dep_year2
## daysalc 24669 23246 20819 16907 24514 23292
## sexuality 23246 41832 34429 25839 41832 41491
## race_eth 20819 34429 45288 23013 40319 34652
## weekhrswrkd 16907 25839 23013 27669 27669 25944
## marst 24514 41832 40319 27669 49581 42182
## dep_year2 23292 41491 34652 25944 42182 42182
##
## $rm
## daysalc sexuality race_eth weekhrswrkd marst dep_year2
## daysalc 0 1423 3850 7762 155 1377
## sexuality 18586 0 7403 15993 0 341
## race_eth 24469 10859 0 22275 4969 10636
## weekhrswrkd 10762 1830 4656 0 0 1725
## marst 25067 7749 9262 21912 0 7399
## dep_year2 18890 691 7530 16238 0 0
##
## $mr
## daysalc sexuality race_eth weekhrswrkd marst dep_year2
## daysalc 0 18586 24469 10762 25067 18890
## sexuality 1423 0 10859 1830 7749 691
## race_eth 3850 7403 0 4656 9262 7530
## weekhrswrkd 7762 15993 22275 0 21912 16238
## marst 155 0 4969 0 0 0
## dep_year2 1377 341 10636 1725 7399 0
##
## $mm
## daysalc sexuality race_eth weekhrswrkd marst dep_year2
## daysalc 31467 12881 6998 20705 6400 12577
## sexuality 12881 14304 3445 12474 6555 13613
## race_eth 6998 3445 10848 6192 1586 3318
## weekhrswrkd 20705 12474 6192 28467 6555 12229
## marst 6400 6555 1586 6555 6555 6555
## dep_year2 12577 13613 3318 12229 6555 13954According to the above marital status and sexuality, race/ethnicity, and depression have extremely high incidences of observing both of those variables at the same time. These results are similar with sexuality and depressive episodes, and depression and marital status. Which is rather interesting. Where one variable is missing and the other is not the highest would be race, and marital status on alcohol usage in the month, and marital status and race with hours worked in a week. Where the first is concerned hours worked in the week and alcohol usage on race, hours worked on a week with marital status. The largest missing among both variables would be in hours worked per week with alcohol usage, and after that it seems very moderate compared to when both variables are concerned. Nothing really higher than 14304 missing variables. in rr the smallest amount of both observed is just above 16000.
Perform a multiple imputation of all values.
dat2<-NSDUH_2019
samp2<-sample(1:dim(dat2)[1], replace = F, size = 500)
dat2$daysalcknock<-dat2$daysalc
dat2$daysalcknock[samp2]<-NA
head(dat2[, c("daysalcknock","daysalc")])## # A tibble: 6 x 2
## daysalcknock daysalc
## <dbl> <dbl>
## 1 20 20
## 2 NA NA
## 3 1 1
## 4 NA NA
## 5 NA NA
## 6 NA NAimp<-mice(data = dat2[,c("daysalc", "sexuality", "race_eth", "weekhrswrkd", "marst", "dep_year2", "educ", "male", "attempt_suicide", "age_cat")], m = 5)##
## iter imp variable
## 1 1 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 1 2 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 1 3 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 1 4 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 1 5 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 2 1 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 2 2 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 2 3 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 2 4 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 2 5 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 3 1 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 3 2 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 3 3 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 3 4 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 3 5 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 4 1 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 4 2 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 4 3 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 4 4 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 4 5 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 5 1 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 5 2 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 5 3 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 5 4 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_cat
## 5 5 daysalc sexuality race_eth weekhrswrkd marst dep_year2 attempt_suicide age_catprint(imp)## Class: mids
## Number of multiple imputations: 5
## Imputation methods:
## daysalc sexuality race_eth weekhrswrkd marst
## "pmm" "polyreg" "polyreg" "pmm" "polyreg"
## dep_year2 educ male attempt_suicide age_cat
## "pmm" "" "" "pmm" "polyreg"
## PredictorMatrix:
## daysalc sexuality race_eth weekhrswrkd marst dep_year2 educ male
## daysalc 0 1 1 1 1 1 1 1
## sexuality 1 0 1 1 1 1 1 1
## race_eth 1 1 0 1 1 1 1 1
## weekhrswrkd 1 1 1 0 1 1 1 1
## marst 1 1 1 1 0 1 1 1
## dep_year2 1 1 1 1 1 0 1 1
## attempt_suicide age_cat
## daysalc 1 1
## sexuality 1 1
## race_eth 1 1
## weekhrswrkd 1 1
## marst 1 1
## dep_year2 1 1head(imp$imp$daysalc)## 1 2 3 4 5
## 2 30 1 1 3 10
## 4 1 4 1 1 3
## 5 5 12 2 2 1
## 6 20 2 11 15 2
## 9 1 15 2 3 1
## 10 10 25 4 1 4summary(imp$imp$daysalc)## 1 2 3 4
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.: 2.000 1st Qu.: 2.000 1st Qu.: 2.000 1st Qu.: 2.000
## Median : 4.000 Median : 4.000 Median : 4.000 Median : 3.000
## Mean : 6.473 Mean : 6.296 Mean : 6.578 Mean : 6.339
## 3rd Qu.: 8.000 3rd Qu.: 8.000 3rd Qu.: 8.000 3rd Qu.: 8.000
## Max. :30.000 Max. :30.000 Max. :30.000 Max. :30.000
## 5
## Min. : 1.000
## 1st Qu.: 2.000
## Median : 4.000
## Mean : 6.369
## 3rd Qu.: 8.000
## Max. :30.000summary(NSDUH_2019$daysalc)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.000 2.000 4.000 7.499 10.000 30.000 31467head(imp$imp$daysalc)## 1 2 3 4 5
## 2 30 1 1 3 10
## 4 1 4 1 1 3
## 5 5 12 2 2 1
## 6 20 2 11 15 2
## 9 1 15 2 3 1
## 10 10 25 4 1 4summary(imp$imp$weekhrswrkd)## 1 2 3 4 5
## Min. : 1.00 Min. : 1.0 Min. : 1.00 Min. : 1.00 Min. : 1.0
## 1st Qu.:16.00 1st Qu.:17.0 1st Qu.:15.00 1st Qu.:17.00 1st Qu.:16.0
## Median :34.00 Median :33.0 Median :32.00 Median :33.00 Median :32.0
## Mean :30.05 Mean :30.3 Mean :29.49 Mean :30.25 Mean :29.5
## 3rd Qu.:40.00 3rd Qu.:40.0 3rd Qu.:40.00 3rd Qu.:40.00 3rd Qu.:40.0
## Max. :61.00 Max. :61.0 Max. :61.00 Max. :61.00 Max. :61.0dat.imp<-complete(imp, action = 1)
head(dat.imp, n=10)## daysalc sexuality race_eth weekhrswrkd marst dep_year2 educ
## 1 20 Heterosexual white 60 married 1 colgrad
## 2 30 Heterosexual mult_race 40 married 0 colgrad
## 3 1 Heterosexual white 40 separated 0 colgrad
## 4 1 Heterosexual white 30 separated 0 LssThnHgh
## 5 5 Heterosexual white 1 separated 0 LssThnHgh
## 6 20 Heterosexual black 40 widowed 1 someCollege
## 7 6 Heterosexual white 59 separated 0 someCollege
## 8 3 Heterosexual white 40 married 0 someCollege
## 9 1 Heterosexual mult_race 40 married 0 colgrad
## 10 10 Heterosexual black 40 married 0 colgrad
## male attempt_suicide age_cat
## 1 Male 0 35-49
## 2 Female 0 65+
## 3 Male 0 30-34
## 4 Female 1 20-21
## 5 Male 1 18-19
## 6 Male 0 50-64
## 7 Female 1 18-19
## 8 Male 0 65+
## 9 Female 0 30-34
## 10 Female 0 35-49head(NSDUH_2019[,c("daysalc", "sexuality", "race_eth", "weekhrswrkd", "marst", "dep_year2", "educ", "male", "attempt_suicide", "age_cat")], n=10)## # A tibble: 10 x 10
## daysalc sexuality race_eth weekhrswrkd marst dep_year2 educ male
## <dbl> <fct> <fct> <dbl> <fct> <dbl> <fct> <fct>
## 1 20 Heterose~ white 60 marr~ 1 colg~ Male
## 2 NA Heterose~ mult_ra~ 40 marr~ 0 colg~ Fema~
## 3 1 Heterose~ white 40 sepa~ 0 colg~ Male
## 4 NA Heterose~ white NA sepa~ 0 LssT~ Fema~
## 5 NA Heterose~ white NA sepa~ 0 LssT~ Male
## 6 NA Heterose~ black 40 wido~ 1 some~ Male
## 7 6 Heterose~ white NA sepa~ 0 some~ Fema~
## 8 3 Heterose~ white NA marr~ 0 some~ Male
## 9 NA Heterose~ mult_ra~ 40 marr~ 0 colg~ Fema~
## 10 NA Heterose~ black NA marr~ 0 colg~ Fema~
## # ... with 2 more variables: attempt_suicide <dbl>, age_cat <fct>fit.daysalc<-with(data=imp ,expr=lm(daysalc~sexuality+weekhrswrkd+marst+race_eth+dep_year2))
fit.daysalc## call :
## with.mids(data = imp, expr = lm(daysalc ~ sexuality + weekhrswrkd +
## marst + race_eth + dep_year2))
##
## call1 :
## mice(data = dat2[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd",
## "marst", "dep_year2", "educ", "male", "attempt_suicide",
## "age_cat")], m = 5)
##
## nmis :
## daysalc sexuality race_eth weekhrswrkd marst
## 31467 14304 10848 28467 6555
## dep_year2 educ male attempt_suicide age_cat
## 13954 0 0 52599 13397
##
## analyses :
## [[1]]
##
## Call:
## lm(formula = daysalc ~ sexuality + weekhrswrkd + marst + race_eth +
## dep_year2)
##
## Coefficients:
## (Intercept) sexualityBisexual sexualityLes/Gay weekhrswrkd
## 6.54239 0.04382 0.48406 0.04351
## marstdivorced marstseparated marstwidowed race_ethasian
## 1.83663 -1.35187 0.55154 -1.58615
## race_ethblack race_ethhispanic race_ethmult_race race_ethother
## -1.45946 -0.36357 -2.20823 -0.87011
## dep_year2
## 0.02271
##
##
## [[2]]
##
## Call:
## lm(formula = daysalc ~ sexuality + weekhrswrkd + marst + race_eth +
## dep_year2)
##
## Coefficients:
## (Intercept) sexualityBisexual sexualityLes/Gay weekhrswrkd
## 6.22908 0.28880 0.79905 0.04723
## marstdivorced marstseparated marstwidowed race_ethasian
## 2.75556 -1.33228 0.72110 -1.73451
## race_ethblack race_ethhispanic race_ethmult_race race_ethother
## -1.50457 -0.35219 -2.18542 -0.70900
## dep_year2
## 0.16423
##
##
## [[3]]
##
## Call:
## lm(formula = daysalc ~ sexuality + weekhrswrkd + marst + race_eth +
## dep_year2)
##
## Coefficients:
## (Intercept) sexualityBisexual sexualityLes/Gay weekhrswrkd
## 6.54765 -0.05434 0.55473 0.04075
## marstdivorced marstseparated marstwidowed race_ethasian
## 2.76989 -1.13284 0.80510 -0.58404
## race_ethblack race_ethhispanic race_ethmult_race race_ethother
## -1.51578 -0.48953 -1.91757 -0.98865
## dep_year2
## -0.08555
##
##
## [[4]]
##
## Call:
## lm(formula = daysalc ~ sexuality + weekhrswrkd + marst + race_eth +
## dep_year2)
##
## Coefficients:
## (Intercept) sexualityBisexual sexualityLes/Gay weekhrswrkd
## 6.15191 0.06830 0.75594 0.04846
## marstdivorced marstseparated marstwidowed race_ethasian
## 2.32075 -1.11213 0.54320 -1.78969
## race_ethblack race_ethhispanic race_ethmult_race race_ethother
## -1.52147 -0.34042 -2.20379 -0.97858
## dep_year2
## 0.06816
##
##
## [[5]]
##
## Call:
## lm(formula = daysalc ~ sexuality + weekhrswrkd + marst + race_eth +
## dep_year2)
##
## Coefficients:
## (Intercept) sexualityBisexual sexualityLes/Gay weekhrswrkd
## 6.26953 0.10083 0.57350 0.04842
## marstdivorced marstseparated marstwidowed race_ethasian
## 2.49319 -1.25716 0.71204 -1.38303
## race_ethblack race_ethhispanic race_ethmult_race race_ethother
## -1.47791 -0.59159 -2.15935 -1.11727
## dep_year2
## -0.07031with (data=imp, exp=(prop.table(table(dep_year2))))## call :
## with.mids(data = imp, expr = (prop.table(table(dep_year2))))
##
## call1 :
## mice(data = dat2[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd",
## "marst", "dep_year2", "educ", "male", "attempt_suicide",
## "age_cat")], m = 5)
##
## nmis :
## daysalc sexuality race_eth weekhrswrkd marst
## 31467 14304 10848 28467 6555
## dep_year2 educ male attempt_suicide age_cat
## 13954 0 0 52599 13397
##
## analyses :
## [[1]]
## dep_year2
## 0 1
## 0.8921191 0.1078809
##
## [[2]]
## dep_year2
## 0 1
## 0.8942212 0.1057788
##
## [[3]]
## dep_year2
## 0 1
## 0.8904446 0.1095554
##
## [[4]]
## dep_year2
## 0 1
## 0.8935264 0.1064736
##
## [[5]]
## dep_year2
## 0 1
## 0.8909078 0.1090922with (data=imp, exp=(prop.table(table(marst))))## call :
## with.mids(data = imp, expr = (prop.table(table(marst))))
##
## call1 :
## mice(data = dat2[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd",
## "marst", "dep_year2", "educ", "male", "attempt_suicide",
## "age_cat")], m = 5)
##
## nmis :
## daysalc sexuality race_eth weekhrswrkd marst
## 31467 14304 10848 28467 6555
## dep_year2 educ male attempt_suicide age_cat
## 13954 0 0 52599 13397
##
## analyses :
## [[1]]
## marst
## married divorced separated widowed
## 0.31854781 0.02629329 0.56833405 0.08682485
##
## [[2]]
## marst
## married divorced separated widowed
## 0.3190288 0.0263111 0.5681559 0.0865042
##
## [[3]]
## marst
## married divorced separated widowed
## 0.31856563 0.02640017 0.56886846 0.08616574
##
## [[4]]
## marst
## married divorced separated widowed
## 0.31927818 0.02656050 0.56755024 0.08661109
##
## [[5]]
## marst
## married divorced separated widowed
## 0.31918911 0.02647143 0.56772837 0.08661109with (data=imp, exp=(prop.table(table(weekhrswrkd))))## call :
## with.mids(data = imp, expr = (prop.table(table(weekhrswrkd))))
##
## call1 :
## mice(data = dat2[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd",
## "marst", "dep_year2", "educ", "male", "attempt_suicide",
## "age_cat")], m = 5)
##
## nmis :
## daysalc sexuality race_eth weekhrswrkd marst
## 31467 14304 10848 28467 6555
## dep_year2 educ male attempt_suicide age_cat
## 13954 0 0 52599 13397
##
## analyses :
## [[1]]
## weekhrswrkd
## 1 2 3 4 5 6
## 0.0076955964 0.0069474134 0.0061636027 0.0135207354 0.0148567764 0.0106527006
## 7 8 9 10 11 12
## 0.0070008551 0.0214300983 0.0083903378 0.0233183697 0.0043465869 0.0190252245
## 13 14 15 16 17 18
## 0.0055223030 0.0064308109 0.0211807040 0.0168341171 0.0038299843 0.0126122274
## 19 20 21 22 23 24
## 0.0021911073 0.0463695311 0.0037052872 0.0034558928 0.0042040758 0.0161393758
## 25 26 27 28 29 30
## 0.0258657546 0.0040971925 0.0038834260 0.0069295995 0.0034737067 0.0522124840
## 31 32 33 34 35 36
## 0.0013182272 0.0185798774 0.0027077098 0.0049522588 0.0316196380 0.0167984894
## 37 38 39 40 41 42
## 0.0090316375 0.0136632464 0.0033490095 0.2773264928 0.0045781673 0.0123984609
## 43 44 45 46 47 48
## 0.0064664386 0.0070364828 0.0456569759 0.0047206784 0.0035984039 0.0144826849
## 49 50 51 52 53 54
## 0.0017992019 0.0547598689 0.0009441357 0.0037943566 0.0009975773 0.0027077098
## 55 56 57 58 59 60
## 0.0112227448 0.0033311957 0.0006412997 0.0015676215 0.0008728801 0.0262398461
## 61
## 0.0305508052
##
## [[2]]
## weekhrswrkd
## 1 2 3 4 5 6
## 0.0062882998 0.0052372809 0.0045959812 0.0122915776 0.0145004988 0.0113118142
## 7 8 9 10 11 12
## 0.0071255522 0.0179920194 0.0094235428 0.0261151489 0.0016923187 0.0170478837
## 13 14 15 16 17 18
## 0.0043109591 0.0071255522 0.0222139091 0.0186867607 0.0055579307 0.0099045176
## 19 20 21 22 23 24
## 0.0028680348 0.0479193387 0.0046850506 0.0040615648 0.0040259370 0.0176713695
## 25 26 27 28 29 30
## 0.0283240701 0.0041150064 0.0042218897 0.0066445775 0.0032243124 0.0537979193
## 31 32 33 34 35 36
## 0.0009263218 0.0180810888 0.0036518455 0.0043109591 0.0334544677 0.0169588143
## 37 38 39 40 41 42
## 0.0094413567 0.0131644577 0.0032777540 0.2776471427 0.0047563061 0.0118996722
## 43 44 45 46 47 48
## 0.0065555081 0.0071968078 0.0440359128 0.0052194670 0.0031530569 0.0136098048
## 49 50 51 52 53 54
## 0.0019060852 0.0543323358 0.0012825994 0.0043109591 0.0009085079 0.0028680348
## 55 56 57 58 59 60
## 0.0116146501 0.0038299843 0.0007838107 0.0014429243 0.0005522303 0.0251353855
## 61
## 0.0307111301
##
## [[3]]
## weekhrswrkd
## 1 2 3 4 5 6
## 0.0100470286 0.0079806185 0.0055757446 0.0164065840 0.0123628331 0.0132713410
## 7 8 9 10 11 12
## 0.0091207069 0.0209491236 0.0058963945 0.0252600827 0.0033668234 0.0180454610
## 13 14 15 16 17 18
## 0.0059676500 0.0075352715 0.0209134958 0.0165312812 0.0054154197 0.0089603819
## 19 20 21 22 23 24
## 0.0033311957 0.0445347014 0.0047028645 0.0034915206 0.0048631894 0.0163887701
## 25 26 27 28 29 30
## 0.0301588998 0.0037409149 0.0061279749 0.0063417415 0.0032243124 0.0523549950
## 31 32 33 34 35 36
## 0.0008016246 0.0172438364 0.0027967793 0.0056470001 0.0312633604 0.0171013254
## 37 38 39 40 41 42
## 0.0081053157 0.0133782243 0.0039546815 0.2739240416 0.0046316089 0.0121490666
## 43 44 45 46 47 48
## 0.0068049024 0.0065198803 0.0424861052 0.0046494228 0.0031530569 0.0141264073
## 49 50 51 52 53 54
## 0.0016388770 0.0515355565 0.0011757161 0.0040259370 0.0011222745 0.0024226878
## 55 56 57 58 59 60
## 0.0113474419 0.0036874733 0.0009263218 0.0019238991 0.0008906940 0.0261329628
## 61
## 0.0315661964
##
## [[4]]
## weekhrswrkd
## 1 2 3 4 5 6
## 0.0053085364 0.0082478267 0.0061636027 0.0143579877 0.0136276186 0.0120778110
## 7 8 9 10 11 12
## 0.0076599686 0.0187402024 0.0064664386 0.0207709848 0.0049166310 0.0178495083
## 13 14 15 16 17 18
## 0.0046316089 0.0073215049 0.0227839533 0.0159968648 0.0034202651 0.0105458173
## 19 20 21 22 23 24
## 0.0023158045 0.0510545817 0.0041684481 0.0048453755 0.0044178424 0.0165312812
## 25 26 27 28 29 30
## 0.0261864044 0.0042753313 0.0039368676 0.0076065270 0.0032064985 0.0531031780
## 31 32 33 34 35 36
## 0.0012113439 0.0195774548 0.0034024512 0.0044712840 0.0307645718 0.0174576030
## 37 38 39 40 41 42
## 0.0075174576 0.0140551518 0.0037052872 0.2775580733 0.0044890979 0.0122203221
## 43 44 45 46 47 48
## 0.0072146216 0.0070542967 0.0450513040 0.0046494228 0.0030996152 0.0143223600
## 49 50 51 52 53 54
## 0.0017635742 0.0537801055 0.0013182272 0.0036874733 0.0009263218 0.0021376657
## 55 56 57 58 59 60
## 0.0111514892 0.0035984039 0.0008728801 0.0020129685 0.0010688328 0.0262220322
## 61
## 0.0311030355
##
## [[5]]
## weekhrswrkd
## 1 2 3 4 5 6
## 0.0098154482 0.0089960097 0.0057538834 0.0117215334 0.0149992874 0.0104389340
## 7 8 9 10 11 12
## 0.0098154482 0.0222851646 0.0055044891 0.0234074391 0.0033133818 0.0240309249
## 13 14 15 16 17 18
## 0.0046494228 0.0070542967 0.0202721961 0.0151239846 0.0039012398 0.0133425966
## 19 20 21 22 23 24
## 0.0026542682 0.0457816731 0.0043465869 0.0052907225 0.0039546815 0.0147320792
## 25 26 27 28 29 30
## 0.0283775118 0.0045247257 0.0031708707 0.0069117857 0.0034024512 0.0555971213
## 31 32 33 34 35 36
## 0.0013004133 0.0184551803 0.0027789654 0.0041506342 0.0289119282 0.0171369531
## 37 38 39 40 41 42
## 0.0078559213 0.0133782243 0.0035627761 0.2758301268 0.0041506342 0.0123984609
## 43 44 45 46 47 48
## 0.0068583440 0.0069652273 0.0441427961 0.0047563061 0.0030639875 0.0135563631
## 49 50 51 52 53 54
## 0.0013716688 0.0537801055 0.0014251104 0.0038299843 0.0010332051 0.0020842240
## 55 56 57 58 59 60
## 0.0116324640 0.0034915206 0.0010688328 0.0015141798 0.0004987887 0.0261685906
## 61
## 0.0296779250with (data=imp, exp=(prop.table(table(sexuality))))## call :
## with.mids(data = imp, expr = (prop.table(table(sexuality))))
##
## call1 :
## mice(data = dat2[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd",
## "marst", "dep_year2", "educ", "male", "attempt_suicide",
## "age_cat")], m = 5)
##
## nmis :
## daysalc sexuality race_eth weekhrswrkd marst
## 31467 14304 10848 28467 6555
## dep_year2 educ male attempt_suicide age_cat
## 13954 0 0 52599 13397
##
## analyses :
## [[1]]
## sexuality
## Heterosexual Bisexual Les/Gay
## 0.90109734 0.07314379 0.02575887
##
## [[2]]
## sexuality
## Heterosexual Bisexual Les/Gay
## 0.90088357 0.07350007 0.02561636
##
## [[3]]
## sexuality
## Heterosexual Bisexual Les/Gay
## 0.90213054 0.07234217 0.02552729
##
## [[4]]
## sexuality
## Heterosexual Bisexual Les/Gay
## 0.90230868 0.07184338 0.02584794
##
## [[5]]
## sexuality
## Heterosexual Bisexual Les/Gay
## 0.90332407 0.07138022 0.02529571with (data=imp, exp=(sd(daysalc)))## call :
## with.mids(data = imp, expr = (sd(daysalc)))
##
## call1 :
## mice(data = dat2[, c("daysalc", "sexuality", "race_eth", "weekhrswrkd",
## "marst", "dep_year2", "educ", "male", "attempt_suicide",
## "age_cat")], m = 5)
##
## nmis :
## daysalc sexuality race_eth weekhrswrkd marst
## 31467 14304 10848 28467 6555
## dep_year2 educ male attempt_suicide age_cat
## 13954 0 0 52599 13397
##
## analyses :
## [[1]]
## [1] 7.286659
##
## [[2]]
## [1] 7.23751
##
## [[3]]
## [1] 7.309172
##
## [[4]]
## [1] 7.278752
##
## [[5]]
## [1] 7.271965est.p<-pool(fit.daysalc)
print(est.p)## Class: mipo m = 5
## term m estimate ubar b t dfcom
## 1 (Intercept) 5 6.34811294 9.278463e-03 3.409896e-02 5.019721e-02 56123
## 2 sexualityBisexual 5 0.08948391 1.422237e-02 1.576851e-02 3.314459e-02 56123
## 3 sexualityLes/Gay 5 0.63345504 3.679300e-02 1.863326e-02 5.915291e-02 56123
## 4 weekhrswrkd 5 0.04567533 4.244323e-06 1.167549e-05 1.825492e-05 56123
## 5 marstdivorced 5 2.43520039 3.761351e-02 1.473495e-01 2.144329e-01 56123
## 6 marstseparated 5 -1.23725588 4.980380e-03 1.228077e-02 1.971730e-02 56123
## 7 marstwidowed 5 0.66659581 1.344125e-02 1.317111e-02 2.924659e-02 56123
## 8 race_ethasian 5 -1.41548346 1.422686e-01 2.408238e-01 4.312572e-01 56123
## 9 race_ethblack 5 -1.49583839 7.038672e-03 6.940084e-04 7.871482e-03 56123
## 10 race_ethhispanic 5 -0.42746115 1.985536e-02 1.202854e-02 3.428961e-02 56123
## 11 race_ethmult_race 5 -2.13487392 1.677497e-02 1.512691e-02 3.492726e-02 56123
## 12 race_ethother 5 -0.93272297 5.449880e-02 2.331481e-02 8.247657e-02 56123
## 13 dep_year2 5 0.01984796 9.867897e-03 1.060649e-02 2.259569e-02 56123
## df riv lambda fmi
## 1 6.016204 4.4100785 0.8151598 0.8561616
## 2 12.266477 1.3304548 0.5708992 0.6271140
## 3 27.972024 0.6077219 0.3780019 0.4181670
## 4 6.787044 3.3010194 0.7674970 0.8150094
## 5 5.879272 4.7009559 0.8245908 0.8641006
## 6 7.156854 2.9589947 0.7474106 0.7971483
## 7 13.689023 1.1758826 0.5404164 0.5954925
## 8 8.903535 2.0312881 0.6701072 0.7255349
## 9 354.812983 0.1183192 0.1058009 0.1107991
## 10 22.557711 0.7269700 0.4209511 0.4662642
## 11 14.800881 1.0821059 0.5197170 0.5736787
## 12 34.728661 0.5133649 0.3392208 0.3742488
## 13 12.600325 1.2898179 0.5632841 0.6192721summary(est.p)## term estimate std.error statistic df
## 1 (Intercept) 6.34811294 0.224047340 28.3338018 6.016204
## 2 sexualityBisexual 0.08948391 0.182056546 0.4915171 12.266477
## 3 sexualityLes/Gay 0.63345504 0.243213720 2.6045202 27.972024
## 4 weekhrswrkd 0.04567533 0.004272577 10.6903457 6.787044
## 5 marstdivorced 2.43520039 0.463069052 5.2588278 5.879272
## 6 marstseparated -1.23725588 0.140418301 -8.8112153 7.156854
## 7 marstwidowed 0.66659581 0.171016344 3.8978486 13.689023
## 8 race_ethasian -1.41548346 0.656701746 -2.1554434 8.903535
## 9 race_ethblack -1.49583839 0.088721374 -16.8599552 354.812983
## 10 race_ethhispanic -0.42746115 0.185174532 -2.3084230 22.557711
## 11 race_ethmult_race -2.13487392 0.186888365 -11.4232575 14.800881
## 12 race_ethother -0.93272297 0.287187336 -3.2477859 34.728661
## 13 dep_year2 0.01984796 0.150318618 0.1320393 12.600325
## p.value
## 1 1.237925e-07
## 2 6.317381e-01
## 3 1.456722e-02
## 4 1.711113e-05
## 5 2.026416e-03
## 6 4.289002e-05
## 7 1.673211e-03
## 8 5.982945e-02
## 9 0.000000e+00
## 10 3.050194e-02
## 11 9.750256e-09
## 12 2.580918e-03
## 13 8.970383e-01lam<-data.frame(lam=est.p$pooled$lambda, param=row.names(est.p$pooled))
ggplot(data=lam,aes(x=param, y=lam))+geom_col()+theme(axis.text.x = element_text(angle = 45, hjust = 1))
bnm<-NSDUH_2019%>%
select(daysalc, dep_year2, marst, sexuality, race_eth)%>%
filter(complete.cases(.))%>%
as.data.frame()
summary(lm(daysalc~dep_year2+marst+sexuality+race_eth, bnm))##
## Call:
## lm(formula = daysalc ~ dep_year2 + marst + sexuality + race_eth,
## data = bnm)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.323 -5.737 -2.991 3.263 24.253
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.7368 0.0890 98.170 < 2e-16 ***
## dep_year2 -0.2485 0.1800 -1.380 0.16748
## marstdivorced 1.5860 0.3750 4.230 2.35e-05 ***
## marstseparated -0.8581 0.1234 -6.956 3.60e-12 ***
## marstwidowed 0.5789 0.1931 2.997 0.00273 **
## sexualityBisexual -0.1391 0.2273 -0.612 0.54075
## sexualityLes/Gay 0.7501 0.3587 2.091 0.03655 *
## race_ethasian -1.7678 0.8372 -2.112 0.03473 *
## race_ethblack -1.8835 0.1711 -11.011 < 2e-16 ***
## race_ethhispanic -0.6148 0.2872 -2.141 0.03228 *
## race_ethmult_race -2.6441 0.2725 -9.703 < 2e-16 ***
## race_ethother -1.0912 0.5164 -2.113 0.03461 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.784 on 19560 degrees of freedom
## Multiple R-squared: 0.018, Adjusted R-squared: 0.01745
## F-statistic: 32.6 on 11 and 19560 DF, p-value: < 2.2e-16Perform the analysis using this imputed data set. What are your results?
fit.imp<-lm(daysalc~dep_year2+marst+sexuality+race_eth, data=dat.imp)
summary(fit.imp)##
## Call:
## lm(formula = daysalc ~ dep_year2 + marst + sexuality + race_eth,
## data = dat.imp)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.052 -4.513 -2.667 1.881 25.831
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.19353 0.05608 146.108 < 2e-16 ***
## dep_year2 -0.02215 0.09984 -0.222 0.824430
## marstdivorced 1.43509 0.19457 7.376 1.66e-13 ***
## marstseparated -1.68001 0.06918 -24.284 < 2e-16 ***
## marstwidowed 0.54653 0.11655 4.689 2.75e-06 ***
## sexualityBisexual -0.06936 0.11941 -0.581 0.561334
## sexualityLes/Gay 0.44549 0.19244 2.315 0.020622 *
## race_ethasian -1.49964 0.38560 -3.889 0.000101 ***
## race_ethblack -1.39469 0.08457 -16.491 < 2e-16 ***
## race_ethhispanic -0.43402 0.14256 -3.044 0.002332 **
## race_ethmult_race -2.25298 0.13057 -17.255 < 2e-16 ***
## race_ethother -0.84623 0.23462 -3.607 0.000310 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.179 on 56124 degrees of freedom
## Multiple R-squared: 0.0295, Adjusted R-squared: 0.02931
## F-statistic: 155.1 on 11 and 56124 DF, p-value: < 2.2e-16fit1<-lm(daysalc.imp.mean~weekhrswrkd.imp.mean+marst.imp+sexuality.imp+race_eth.imp, data=NSDUH_2019)
summary(fit1)##
## Call:
## lm(formula = daysalc.imp.mean ~ weekhrswrkd.imp.mean + marst.imp +
## sexuality.imp + race_eth.imp, data = NSDUH_2019)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.9744 -2.3578 0.1252 0.4481 23.6594
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.067635 0.093612 75.499 < 2e-16 ***
## weekhrswrkd.imp.mean 0.021990 0.002192 10.031 < 2e-16 ***
## marst.impdivorced 0.565434 0.143205 3.948 7.88e-05 ***
## marst.impseparated -0.522741 0.048585 -10.759 < 2e-16 ***
## marst.impwidowed 0.234434 0.084421 2.777 0.00549 **
## sexuality.impBisexual 0.026877 0.100472 0.268 0.78908
## sexuality.impLes/Gay 0.484268 0.162586 2.979 0.00290 **
## race_eth.impasian -0.307911 0.295196 -1.043 0.29692
## race_eth.impblack -0.468150 0.064271 -7.284 3.28e-13 ***
## race_eth.imphispanic -0.064021 0.110175 -0.581 0.56119
## race_eth.impmult_race -0.737357 0.099926 -7.379 1.62e-13 ***
## race_eth.impother -0.184120 0.185001 -0.995 0.31962
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.027 on 56124 degrees of freedom
## Multiple R-squared: 0.008658, Adjusted R-squared: 0.008464
## F-statistic: 44.56 on 11 and 56124 DF, p-value: < 2.2e-16