HRS data analysis
Ali
2022-09-26
Link
#https://hrsdata.isr.umich.edu/data-products/2020-hrs-corelibraries
library(haven)# used for dta or stata data## Warning: package 'haven' was built under R version 4.2.2library(dplyr)# for data management##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(car)# recoding and renaming## Warning: package 'car' was built under R version 4.2.2## Loading required package: carData## Warning: package 'carData' was built under R version 4.2.2##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recodelibrary(compareGroups)# making table## Warning: package 'compareGroups' was built under R version 4.2.2library(foreign)# recode functionRead data
2F. Identification Variables The primary Identification variables (IDs) are: HHID PN HOUSEHOLD IDENTIFIER PERSON NUMBER Records in the data files are sorted in order by HHID and PN. Identification variables in the 2020 HRS COVID-19 Project data are stored in character format.
main_data <- read_dta(file = "C:/Users/ali_r/Downloads/trk2020tr_r.dta")
nrow(main_data)## [1] 43559baseline<-main_data %>%
filter(PN=="010")
# data for PA
HRS_RC <- read_dta(file = "C:/Users/ali_r/Downloads/h20C_r.dta")
# number of rows in the dataset
nrow(HRS_RC)## [1] 15723# Filter data by pn==10
HRS_RC_new<-HRS_RC %>%
filter(pn=="010")
# data for demo
HRS_demo <- read_dta(file = "C:/Users/ali_r/Downloads/h20b_r.dta")
nrow(HRS_demo)## [1] 15723HRS_demo_new<-HRS_demo %>%
filter(pn=="010")
# data join
df_full<- full_join(HRS_RC_new, HRS_demo_new, by="hhid")
head(df_full)## # A tibble: 6 × 429
## hhid pn.x rsubhh.x qsubh…¹ RPN_S…² rcsr.x rfamr.x rfinr.x RC231 RC234 RC235
## <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 010038 010 0 0 "040" 1 5 1 1 0 1
## 2 010050 010 0 0 "" 1 1 1 1 0 1
## 3 010106 010 0 0 "020" 5 1 1 1 0 1
## 4 010299 010 1 1 "" 1 1 1 1 0 1
## 5 010372 010 0 0 "" 1 1 1 1 0 1
## 6 010397 010 0 0 "" 1 1 1 1 0 1
## # … with 418 more variables: RC239 <dbl>, RC248 <dbl>, RC185 <dbl>,
## # RC001 <dbl>, RC002 <dbl>, RC005 <dbl>, RC006 <dbl>, RC010 <dbl>,
## # RC285 <dbl>, RC011 <dbl>, RC012 <dbl>, RC236 <dbl>, RC214 <dbl>,
## # RC018 <dbl>, RC019 <dbl>, RC020 <dbl>, RC021M1 <dbl>, RC021M2 <dbl>,
## # RC021M3 <dbl>, RC021M4 <dbl>, RC021M5 <dbl>, RC021M6 <dbl>, RC021M7 <dbl>,
## # RC023 <dbl>, RC024 <dbl>, RC028 <dbl>, RC029 <dbl>, RC030 <dbl>,
## # RC031 <dbl>, RC032 <dbl>, RC033 <dbl>, RC034 <dbl>, RC036 <dbl>, …head(baseline)## # A tibble: 6 × 552
## HHID PN BIRTHMO BIRTHYR DEGREE EFTFASSIGN EXDEA…¹ EXDEA…² EXDOD…³ FIRSTIW
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 000001 010 2 1938 4 9 4 1995 1 1992
## 2 000002 010 10 1934 0 9 11 2001 1 1992
## 3 000003 010 1 1936 2 1 8 2013 1 1992
## 4 010001 010 6 1939 2 2 NA NA NA 1992
## 5 010004 010 12 1939 4 1 9 2011 1 1992
## 6 010013 010 3 1938 2 1 3 2016 1 1992
## # … with 542 more variables: GENDER <dbl>, HISPANIC <dbl>, IMMGYEAR <dbl>,
## # KNOWNDECEASEDMO <dbl>, KNOWNDECEASEDYR <dbl>, KNOWNDECEASEDSOURCE <dbl>,
## # LASTALIVEMO <dbl>, LASTALIVEYR <dbl>, LASTALIVESOURCE <dbl>, MOSFLAG <dbl>,
## # OVHHID <chr>, OVPN <chr>, OVRESULT <dbl>, OVYEAR <dbl>, RACE <dbl>,
## # SCHLYRS <dbl>, SECU <dbl>, STRATUM <dbl>, STUDY <dbl>, USBORN <dbl>,
## # WTCOHORT <dbl>, YRENTER <dbl>, ADAMS1 <dbl>, CAMS01 <dbl>, CAMS03 <dbl>,
## # CAMS05 <dbl>, CAMS07 <dbl>, CAMS09 <dbl>, CAMS11 <dbl>, CAMS13 <dbl>, …# renaming ID variable in baseline
baseline<- baseline %>%
rename(hhid= HHID)
head(baseline)## # A tibble: 6 × 552
## hhid PN BIRTHMO BIRTHYR DEGREE EFTFASSIGN EXDEA…¹ EXDEA…² EXDOD…³ FIRSTIW
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 000001 010 2 1938 4 9 4 1995 1 1992
## 2 000002 010 10 1934 0 9 11 2001 1 1992
## 3 000003 010 1 1936 2 1 8 2013 1 1992
## 4 010001 010 6 1939 2 2 NA NA NA 1992
## 5 010004 010 12 1939 4 1 9 2011 1 1992
## 6 010013 010 3 1938 2 1 3 2016 1 1992
## # … with 542 more variables: GENDER <dbl>, HISPANIC <dbl>, IMMGYEAR <dbl>,
## # KNOWNDECEASEDMO <dbl>, KNOWNDECEASEDYR <dbl>, KNOWNDECEASEDSOURCE <dbl>,
## # LASTALIVEMO <dbl>, LASTALIVEYR <dbl>, LASTALIVESOURCE <dbl>, MOSFLAG <dbl>,
## # OVHHID <chr>, OVPN <chr>, OVRESULT <dbl>, OVYEAR <dbl>, RACE <dbl>,
## # SCHLYRS <dbl>, SECU <dbl>, STRATUM <dbl>, STUDY <dbl>, USBORN <dbl>,
## # WTCOHORT <dbl>, YRENTER <dbl>, ADAMS1 <dbl>, CAMS01 <dbl>, CAMS03 <dbl>,
## # CAMS05 <dbl>, CAMS07 <dbl>, CAMS09 <dbl>, CAMS11 <dbl>, CAMS13 <dbl>, …# data join
df_full<- left_join(df_full, baseline, by="hhid")make a new dataset for our research
df_final<-df_full %>%
select(hhid, RC001, RC272, RC273, RC079 , RC080 , RC081 , RC082, GENDER , BIRTHYR, DEGREE, RC298, RC210, RACE )Coding
table(df_final$RC001)##
## 1 2 3 4 5 8 9
## 576 2511 3119 2051 573 7 2hist(df_final$RC001)
# Make general health
df_final$general_heath<-Recode(df_final$RC001, recodes="1:3='good';4:5='bad';8:9=NA; else= 'No'",as.factor=T)
# Make alzhaimer
table(df_final$RC272)##
## -8 1 4 5 8
## 7 129 3 8696 4df_final$ALZHEIMERS<-Recode(df_final$RC272, recodes="1='Yes';4:5='No';-8=NA;8=NA; else= 'No'",as.factor=T)
df_final$PRESCRIPTION_MEMORYPROBLEM<-Recode(df_final$RC298, recodes="1='Yes';4:5='No';-8=NA;8=NA; else= 'No'",as.factor=T)
df_final$PRESCRIPTION_MEMORYPROBLEM1<-Recode(df_final$RC210, recodes="1='Yes';4:5='No';-8=NA;8=NA; else= 'No'",as.factor=T)
table(df_final$ALZHEIMERS, exclude = NULL)##
## No Yes <NA>
## 8699 129 11# Make DEMENTIA
table(df_final$RC273)##
## -8 1 4 5 8 9
## 5 227 7 8460 10 1df_final$DEMENTIA<-Recode(df_final$RC273, recodes="1='Yes';4:5='No';-8=NA;8=NA;9=NA; else= 'No'",as.factor=T)
# make FALLEN
table(df_final$RC079)##
## -8 1 5 8 9
## 5 1734 3128 9 2df_final$FALLEN<-Recode(df_final$RC079, recodes="1='Yes';5='No';-8=NA;8=NA;9=NA; else= 'No' ",as.factor=T)
table(df_final$FALLEN, exclude = NULL)##
## No Yes <NA>
## 7089 1734 16# number of fall
table(df_final$RC080)##
## -8 0 1 2 3 4 5 6 7 8 9 10 11 12 15 18 20 24 25 30
## 2 5 537 467 275 122 78 58 12 12 1 56 2 22 10 1 11 2 3 6
## 35 40 48 50 98 99
## 1 1 1 6 40 3df_final$FALLEN_num<-Recode(df_final$RC080, recodes="NA=0;-8=NA",as.numeric=T)
table(df_final$FALLEN_num)##
## 0 1 2 3 4 5 6 7 8 9 10 11 12 15 18 20
## 7110 537 467 275 122 78 58 12 12 1 56 2 22 10 1 11
## 24 25 30 35 40 48 50 98 99
## 2 3 6 1 1 1 6 40 3hist(df_final$FALLEN_num)
# injury fall
table(df_final$RC081)##
## -8 1 5 8
## 1 531 1196 6df_final$FALLEN_injury<-Recode(df_final$RC081, recodes="1='Yes';5='No';-8=NA;8=NA; else= 'No'",as.factor=T)
table(df_final$FALLEN_injury)##
## No Yes
## 8301 531# hip
table(df_final$RC082)##
## -8 1 5 8 9
## 1 59 4810 7 1df_final$HIP<-Recode(df_final$RC082, recodes="1='Yes';5='No';-8=NA;8=NA;9=NA; else= 'No'",as.factor=T)
table(df_final$HIP)##
## No Yes
## 8771 59df_final %>%
select(general_heath, RC001)## # A tibble: 8,839 × 2
## general_heath RC001
## <fct> <dbl>
## 1 good 2
## 2 good 3
## 3 bad 4
## 4 bad 4
## 5 good 3
## 6 bad 4
## 7 good 3
## 8 good 2
## 9 good 2
## 10 good 3
## # … with 8,829 more rowstable(df_final$general_heath, exclude = NULL)##
## bad good <NA>
## 2624 6206 9# Degree
df_final$DEGREE<-Recode(df_final$DEGREE, recodes="0='LTHS';1:2='HS'; else= 'COLACA'",as.factor=T)
table(df_final$DEGREE, exclude = NULL)##
## COLACA HS LTHS
## 3520 3949 1370df_final$RACE<-Recode(df_final$RACE, recodes="1='White';2='Black'; else= 'Other'",as.factor=T)
table(df_final$DEGREE, exclude = NULL)##
## COLACA HS LTHS
## 3520 3949 1370Code demography
# education
table(df_final$GENDER, exclude = NULL)##
## 1 2
## 4004 4835df_final$GENDER<-Recode(df_final$GENDER, recodes="1='Male';2='Female'",as.factor=T)
# make age
df_final$Age<- 2022 - (df_final$BIRTHYR)
df_final %>%
select(BIRTHYR, Age)## # A tibble: 8,839 × 2
## BIRTHYR Age
## <dbl> <dbl>
## 1 1936 86
## 2 1941 81
## 3 1931 91
## 4 1940 82
## 5 1935 87
## 6 1941 81
## 7 1939 83
## 8 1938 84
## 9 1937 85
## 10 1940 82
## # … with 8,829 more rowslibrary(compareGroups)
resu1 <- compareGroups(~., data = df_final,
method = c(waist = 2))## Warning in compareGroups.fit(X = X, y = y, include.label = include.label, :
## variables waist specified in 'method' not found## Warning in compareGroups.fit(X = X, y = y, include.label = include.label, :
## Variables 'hhid' have been removed since some errors occurredcreateTable(resu1)##
## --------Summary descriptives table ---------
##
## _________________________________________________
## [ALL] N
## N=8839
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## RATE HEALTH 2.95 (1.03) 8839
## EVER HAD ALZHEIMERS 4.93 (0.61) 8839
## EVER HAD DEMENTIA 4.89 (0.72) 8710
## FALLEN IN PAST TWO YEARS 3.57 (1.96) 4878
## NUMBER TIMES FALLEN 5.69 (15.5) 1734
## INJURY DUE TO FALL 3.78 (1.88) 1734
## BROKEN HIP 4.95 (0.49) 4878
## GENDER: 8839
## Female 4835 (54.7%)
## Male 4004 (45.3%)
## BIRTHDATE: YEAR 1952 (10.1) 8839
## DEGREE: 8839
## COLACA 3520 (39.8%)
## HS 3949 (44.7%)
## LTHS 1370 (15.5%)
## PRESCRIPTION FOR MEMORY PROBLEM 2.55 (1.98) 132
## PRESCRIPTION FOR MEMORY PROBLEM 3.14 (2.10) 363
## RACE: 8839
## Black 2292 (25.9%)
## Other 1175 (13.3%)
## White 5372 (60.8%)
## general_heath: 8830
## bad 2624 (29.7%)
## good 6206 (70.3%)
## ALZHEIMERS: 8828
## No 8699 (98.5%)
## Yes 129 (1.46%)
## PRESCRIPTION_MEMORYPROBLEM: 8838
## No 8757 (99.1%)
## Yes 81 (0.92%)
## PRESCRIPTION_MEMORYPROBLEM1: 8831
## No 8658 (98.0%)
## Yes 173 (1.96%)
## DEMENTIA: 8823
## No 8596 (97.4%)
## Yes 227 (2.57%)
## FALLEN: 8823
## No 7089 (80.3%)
## Yes 1734 (19.7%)
## NUMBER TIMES FALLEN 1.12 (7.21) 8837
## FALLEN_injury: 8832
## No 8301 (94.0%)
## Yes 531 (6.01%)
## HIP: 8830
## No 8771 (99.3%)
## Yes 59 (0.67%)
## BIRTHDATE: YEAR 70.5 (10.1) 8839
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯xx<-df_final %>%
select(FALLEN, FALLEN_injury,FALLEN_num,DEMENTIA,ALZHEIMERS, PRESCRIPTION_MEMORYPROBLEM, PRESCRIPTION_MEMORYPROBLEM1, Age, GENDER,RACE,DEGREE )
table(xx$FALLEN, exclude = NULL)##
## No Yes <NA>
## 7089 1734 16y<-na.omit(xx)
library(table1)## Warning: package 'table1' was built under R version 4.2.2##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1(~ FALLEN+FALLEN_injury+FALLEN_num+DEMENTIA+ALZHEIMERS+ PRESCRIPTION_MEMORYPROBLEM+ PRESCRIPTION_MEMORYPROBLEM1+ Age+ GENDER+RACE+DEGREE , data=y)| Overall (N=8782) |
|
|---|---|
| FALLEN | |
| No | 7067 (80.5%) |
| Yes | 1715 (19.5%) |
| FALLEN_injury | |
| No | 8256 (94.0%) |
| Yes | 526 (6.0%) |
| NUMBER TIMES FALLEN | |
| Mean (SD) | 1.10 (7.08) |
| Median [Min, Max] | 0 [0, 99.0] |
| DEMENTIA | |
| No | 8565 (97.5%) |
| Yes | 217 (2.5%) |
| ALZHEIMERS | |
| No | 8654 (98.5%) |
| Yes | 128 (1.5%) |
| PRESCRIPTION_MEMORYPROBLEM | |
| No | 8701 (99.1%) |
| Yes | 81 (0.9%) |
| PRESCRIPTION_MEMORYPROBLEM1 | |
| No | 8611 (98.1%) |
| Yes | 171 (1.9%) |
| BIRTHDATE: YEAR | |
| Mean (SD) | 70.4 (10.1) |
| Median [Min, Max] | 68.0 [37.0, 106] |
| GENDER | |
| Female | 4807 (54.7%) |
| Male | 3975 (45.3%) |
| RACE | |
| Black | 2282 (26.0%) |
| Other | 1169 (13.3%) |
| White | 5331 (60.7%) |
| DEGREE | |
| COLACA | 3499 (39.8%) |
| HS | 3919 (44.6%) |
| LTHS | 1364 (15.5%) |
df_final$FALLENNUM<-as.numeric(df_final$FALLEN)
df_final$FALLENNUM<-Recode(df_final$FALLENNUM, recodes="2=1;1=0",as.numeric=T)
#df_final <- df_final[complete.cases(df_final), ]
df_final %>%
select(FALLENNUM, FALLEN, ALZHEIMERS)## # A tibble: 8,839 × 3
## FALLENNUM FALLEN ALZHEIMERS
## <dbl> <fct> <fct>
## 1 0 No No
## 2 0 No No
## 3 0 No No
## 4 0 No No
## 5 0 No No
## 6 0 No No
## 7 0 No No
## 8 0 No No
## 9 1 Yes No
## 10 0 No No
## # … with 8,829 more rows#df_final$FALLENNUM<-as.numeric(df_final$FALLENNUM)MODEL_FALL_UNADJ<- lm(FALLENNUM~ALZHEIMERS+DEMENTIA+PRESCRIPTION_MEMORYPROBLEM+PRESCRIPTION_MEMORYPROBLEM1, data = df_final)
summary(MODEL_FALL_UNADJ)##
## Call:
## lm(formula = FALLENNUM ~ ALZHEIMERS + DEMENTIA + PRESCRIPTION_MEMORYPROBLEM +
## PRESCRIPTION_MEMORYPROBLEM1, data = df_final)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5926 -0.1854 -0.1854 -0.1854 0.8146
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.185435 0.004279 43.336 < 2e-16 ***
## ALZHEIMERSYes 0.303927 0.057518 5.284 1.29e-07 ***
## DEMENTIAYes 0.168896 0.035155 4.804 1.58e-06 ***
## PRESCRIPTION_MEMORYPROBLEMYes -0.003977 0.090088 -0.044 0.9648
## PRESCRIPTION_MEMORYPROBLEM1Yes 0.107208 0.054007 1.985 0.0472 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3932 on 8786 degrees of freedom
## (48 observations deleted due to missingness)
## Multiple R-squared: 0.01972, Adjusted R-squared: 0.01927
## F-statistic: 44.18 on 4 and 8786 DF, p-value: < 2.2e-16exp(coef(MODEL_FALL_UNADJ))## (Intercept) ALZHEIMERSYes
## 1.203742 1.355169
## DEMENTIAYes PRESCRIPTION_MEMORYPROBLEMYes
## 1.183996 0.996031
## PRESCRIPTION_MEMORYPROBLEM1Yes
## 1.113165MODEL_FALL_ADJ<- lm(FALLENNUM~ALZHEIMERS+DEMENTIA+PRESCRIPTION_MEMORYPROBLEM+PRESCRIPTION_MEMORYPROBLEM1+Age+GENDER+DEGREE+RACE, data = df_final)
summary(MODEL_FALL_ADJ)##
## Call:
## lm(formula = FALLENNUM ~ ALZHEIMERS + DEMENTIA + PRESCRIPTION_MEMORYPROBLEM +
## PRESCRIPTION_MEMORYPROBLEM1 + Age + GENDER + DEGREE + RACE,
## data = df_final)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.89553 -0.19984 -0.07998 0.01131 0.90414
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.9404197 0.0284126 -33.099 < 2e-16 ***
## ALZHEIMERSYes 0.1512884 0.0526933 2.871 0.004100 **
## DEMENTIAYes 0.1083655 0.0321414 3.372 0.000751 ***
## PRESCRIPTION_MEMORYPROBLEMYes 0.0253505 0.0822860 0.308 0.758030
## PRESCRIPTION_MEMORYPROBLEM1Yes 0.0146201 0.0493696 0.296 0.767134
## Age 0.0158757 0.0004072 38.986 < 2e-16 ***
## GENDERMale -0.0273950 0.0077361 -3.541 0.000400 ***
## DEGREEHS 0.0115494 0.0085121 1.357 0.174873
## DEGREELTHS -0.0035987 0.0117725 -0.306 0.759852
## RACEOther 0.0241940 0.0130313 1.857 0.063400 .
## RACEWhite 0.0289597 0.0092165 3.142 0.001683 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.359 on 8780 degrees of freedom
## (48 observations deleted due to missingness)
## Multiple R-squared: 0.1833, Adjusted R-squared: 0.1824
## F-statistic: 197.1 on 10 and 8780 DF, p-value: < 2.2e-16exp(coef(MODEL_FALL_ADJ))## (Intercept) ALZHEIMERSYes
## 0.3904639 1.1633321
## DEMENTIAYes PRESCRIPTION_MEMORYPROBLEMYes
## 1.1144550 1.0256746
## PRESCRIPTION_MEMORYPROBLEM1Yes Age
## 1.0147275 1.0160024
## GENDERMale DEGREEHS
## 0.9729769 1.0116164
## DEGREELTHS RACEOther
## 0.9964078 1.0244891
## RACEWhite
## 1.0293831df_final$FALLEN_injuryNUM<-as.numeric(df_final$FALLEN_injury)
df_final$FALLEN_injuryNUM<-Recode(df_final$FALLEN_injuryNUM, recodes="2=1;1=0",as.numeric=T)
#df_final <- df_final[complete.cases(df_final), ]
df_final %>%
select(FALLEN_injuryNUM, FALLEN_injury, ALZHEIMERS)## # A tibble: 8,839 × 3
## FALLEN_injuryNUM FALLEN_injury ALZHEIMERS
## <dbl> <fct> <fct>
## 1 0 No No
## 2 0 No No
## 3 0 No No
## 4 0 No No
## 5 0 No No
## 6 0 No No
## 7 0 No No
## 8 0 No No
## 9 0 No No
## 10 0 No No
## # … with 8,829 more rows#df_final$FALLENNUM<-as.numeric(df_final$FALLENNUM)MODEL_FALL_UNADJ<- lm(FALLEN_injuryNUM~ALZHEIMERS+DEMENTIA+PRESCRIPTION_MEMORYPROBLEM+PRESCRIPTION_MEMORYPROBLEM1, data = df_final)
summary(MODEL_FALL_UNADJ)##
## Call:
## lm(formula = FALLEN_injuryNUM ~ ALZHEIMERS + DEMENTIA + PRESCRIPTION_MEMORYPROBLEM +
## PRESCRIPTION_MEMORYPROBLEM1, data = df_final)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.2469 -0.0543 -0.0543 -0.0543 0.9457
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.054300 0.002561 21.206 < 2e-16 ***
## ALZHEIMERSYes 0.073359 0.034435 2.130 0.0332 *
## DEMENTIAYes 0.103180 0.021046 4.903 9.63e-07 ***
## PRESCRIPTION_MEMORYPROBLEMYes 0.045965 0.053933 0.852 0.3941
## PRESCRIPTION_MEMORYPROBLEM1Yes 0.073289 0.032333 2.267 0.0234 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2354 on 8794 degrees of freedom
## (40 observations deleted due to missingness)
## Multiple R-squared: 0.01452, Adjusted R-squared: 0.01407
## F-statistic: 32.39 on 4 and 8794 DF, p-value: < 2.2e-16exp(coef(MODEL_FALL_UNADJ))## (Intercept) ALZHEIMERSYes
## 1.055802 1.076117
## DEMENTIAYes PRESCRIPTION_MEMORYPROBLEMYes
## 1.108691 1.047038
## PRESCRIPTION_MEMORYPROBLEM1Yes
## 1.076041MODEL_FALL_ADJ<- lm(FALLEN_injuryNUM~ALZHEIMERS+DEMENTIA+PRESCRIPTION_MEMORYPROBLEM+PRESCRIPTION_MEMORYPROBLEM1+Age+GENDER+DEGREE+RACE, data = df_final)
summary(MODEL_FALL_ADJ)##
## Call:
## lm(formula = FALLEN_injuryNUM ~ ALZHEIMERS + DEMENTIA + PRESCRIPTION_MEMORYPROBLEM +
## PRESCRIPTION_MEMORYPROBLEM1 + Age + GENDER + DEGREE + RACE,
## data = df_final)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.35317 -0.08564 -0.03928 -0.00922 0.99243
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.2917457 0.0181578 -16.067 < 2e-16 ***
## ALZHEIMERSYes 0.0254275 0.0336934 0.755 0.450465
## DEMENTIAYes 0.0834422 0.0205519 4.060 4.95e-05 ***
## PRESCRIPTION_MEMORYPROBLEMYes 0.0528788 0.0526176 1.005 0.314942
## PRESCRIPTION_MEMORYPROBLEM1Yes 0.0466076 0.0315686 1.476 0.139875
## Age 0.0049684 0.0002602 19.098 < 2e-16 ***
## GENDERMale -0.0318180 0.0049442 -6.435 1.30e-10 ***
## DEGREEHS -0.0050838 0.0054390 -0.935 0.349974
## DEGREELTHS -0.0067200 0.0075251 -0.893 0.371873
## RACEOther 0.0259599 0.0083298 3.117 0.001836 **
## RACEWhite 0.0197704 0.0058919 3.356 0.000795 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2296 on 8788 degrees of freedom
## (40 observations deleted due to missingness)
## Multiple R-squared: 0.06338, Adjusted R-squared: 0.06231
## F-statistic: 59.47 on 10 and 8788 DF, p-value: < 2.2e-16exp(coef(MODEL_FALL_ADJ))## (Intercept) ALZHEIMERSYes
## 0.7469585 1.0257535
## DEMENTIAYes PRESCRIPTION_MEMORYPROBLEMYes
## 1.0870224 1.0543018
## PRESCRIPTION_MEMORYPROBLEM1Yes Age
## 1.0477108 1.0049808
## GENDERMale DEGREEHS
## 0.9686829 0.9949291
## DEGREELTHS RACEOther
## 0.9933025 1.0262998
## RACEWhite
## 1.0199671MODEL_FALL_UNADJ<- lm(FALLEN_num~ALZHEIMERS+DEMENTIA+PRESCRIPTION_MEMORYPROBLEM+PRESCRIPTION_MEMORYPROBLEM1, data = df_final)
summary(MODEL_FALL_UNADJ)##
## Call:
## lm(formula = FALLEN_num ~ ALZHEIMERS + DEMENTIA + PRESCRIPTION_MEMORYPROBLEM +
## PRESCRIPTION_MEMORYPROBLEM1, data = df_final)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.170 -0.944 -0.944 -0.944 98.056
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.94419 0.07633 12.369 < 2e-16 ***
## ALZHEIMERSYes 9.22602 1.02677 8.986 < 2e-16 ***
## DEMENTIAYes 2.44951 0.62756 3.903 9.56e-05 ***
## PRESCRIPTION_MEMORYPROBLEMYes -5.91527 1.60636 -3.682 0.000232 ***
## PRESCRIPTION_MEMORYPROBLEM1Yes 0.58456 0.96105 0.608 0.543035
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.02 on 8799 degrees of freedom
## (35 observations deleted due to missingness)
## Multiple R-squared: 0.01507, Adjusted R-squared: 0.01462
## F-statistic: 33.66 on 4 and 8799 DF, p-value: < 2.2e-16exp(coef(MODEL_FALL_UNADJ))## (Intercept) ALZHEIMERSYes
## 2.570726e+00 1.015808e+04
## DEMENTIAYes PRESCRIPTION_MEMORYPROBLEMYes
## 1.158270e+01 2.697940e-03
## PRESCRIPTION_MEMORYPROBLEM1Yes
## 1.794202e+00MODEL_FALL_ADJ<- lm(FALLEN_num~ALZHEIMERS+DEMENTIA+PRESCRIPTION_MEMORYPROBLEM+PRESCRIPTION_MEMORYPROBLEM1+Age+GENDER+DEGREE+RACE, data = df_final)
summary(MODEL_FALL_ADJ)##
## Call:
## lm(formula = FALLEN_num ~ ALZHEIMERS + DEMENTIA + PRESCRIPTION_MEMORYPROBLEM +
## PRESCRIPTION_MEMORYPROBLEM1 + Age + GENDER + DEGREE + RACE,
## data = df_final)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11.826 -1.151 -0.478 -0.044 98.246
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -5.043919 0.550989 -9.154 < 2e-16 ***
## ALZHEIMERSYes 8.442300 1.022689 8.255 < 2e-16 ***
## DEMENTIAYes 2.132225 0.623809 3.418 0.000634 ***
## PRESCRIPTION_MEMORYPROBLEMYes -5.780542 1.595263 -3.624 0.000292 ***
## PRESCRIPTION_MEMORYPROBLEM1Yes 0.093093 0.955180 0.097 0.922363
## Age 0.085147 0.007895 10.785 < 2e-16 ***
## GENDERMale -0.141479 0.150035 -0.943 0.345723
## DEGREEHS -0.126152 0.165052 -0.764 0.444699
## DEGREELTHS -0.087076 0.228358 -0.381 0.702979
## RACEOther 0.072572 0.252804 0.287 0.774067
## RACEWhite 0.234162 0.178766 1.310 0.190272
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.969 on 8793 degrees of freedom
## (35 observations deleted due to missingness)
## Multiple R-squared: 0.03002, Adjusted R-squared: 0.02891
## F-statistic: 27.21 on 10 and 8793 DF, p-value: < 2.2e-16exp(coef(MODEL_FALL_ADJ))## (Intercept) ALZHEIMERSYes
## 6.448427e-03 4.639212e+03
## DEMENTIAYes PRESCRIPTION_MEMORYPROBLEMYes
## 8.433607e+00 3.087043e-03
## PRESCRIPTION_MEMORYPROBLEM1Yes Age
## 1.097564e+00 1.088877e+00
## GENDERMale DEGREEHS
## 8.680738e-01 8.814810e-01
## DEGREELTHS RACEOther
## 9.166072e-01 1.075270e+00
## RACEWhite
## 1.263849e+00library(compareGroups)
resu1 <- compareGroups(FALLEN~Age+GENDER+ALZHEIMERS+DEMENTIA+general_heath+FALLEN_num+HIP, data = df_final,
method = c(waist = 2))## Warning in compareGroups.fit(X = X, y = y, include.label = include.label, :
## variables waist specified in 'method' not found## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredcreateTable(resu1)##
## --------Summary descriptives table by 'FALLEN'---------
##
## _______________________________________________________
## No Yes p.overall
## N=7089 N=1734
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## BIRTHDATE: YEAR 68.3 (9.32) 79.0 (8.27) 0.000
## GENDER: 0.002
## Female 3823 (53.9%) 1006 (58.0%)
## Male 3266 (46.1%) 728 (42.0%)
## ALZHEIMERS: <0.001
## No 7024 (99.2%) 1659 (95.8%)
## Yes 57 (0.80%) 72 (4.16%)
## DEMENTIA: <0.001
## No 6943 (98.1%) 1639 (94.7%)
## Yes 135 (1.91%) 91 (5.26%)
## general_heath: <0.001
## bad 1949 (27.5%) 670 (38.7%)
## good 5133 (72.5%) 1063 (61.3%)
## NUMBER TIMES FALLEN 0.00 (0.00) 5.71 (15.5) <0.001
## HIP: <0.001
## No 7076 (99.9%) 1679 (97.2%)
## Yes 10 (0.14%) 49 (2.84%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯library(compareGroups)
resu1 <- compareGroups(~., data = df_final,
method = c(waist = 2))## Warning in compareGroups.fit(X = X, y = y, include.label = include.label, :
## variables waist specified in 'method' not found## Warning in compareGroups.fit(X = X, y = y, include.label = include.label, :
## Variables 'hhid' have been removed since some errors occurredcreateTable(resu1)##
## --------Summary descriptives table ---------
##
## _________________________________________________
## [ALL] N
## N=8839
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## RATE HEALTH 2.95 (1.03) 8839
## EVER HAD ALZHEIMERS 4.93 (0.61) 8839
## EVER HAD DEMENTIA 4.89 (0.72) 8710
## FALLEN IN PAST TWO YEARS 3.57 (1.96) 4878
## NUMBER TIMES FALLEN 5.69 (15.5) 1734
## INJURY DUE TO FALL 3.78 (1.88) 1734
## BROKEN HIP 4.95 (0.49) 4878
## GENDER: 8839
## Female 4835 (54.7%)
## Male 4004 (45.3%)
## BIRTHDATE: YEAR 1952 (10.1) 8839
## DEGREE: 8839
## COLACA 3520 (39.8%)
## HS 3949 (44.7%)
## LTHS 1370 (15.5%)
## PRESCRIPTION FOR MEMORY PROBLEM 2.55 (1.98) 132
## PRESCRIPTION FOR MEMORY PROBLEM 3.14 (2.10) 363
## RACE: 8839
## Black 2292 (25.9%)
## Other 1175 (13.3%)
## White 5372 (60.8%)
## general_heath: 8830
## bad 2624 (29.7%)
## good 6206 (70.3%)
## ALZHEIMERS: 8828
## No 8699 (98.5%)
## Yes 129 (1.46%)
## PRESCRIPTION_MEMORYPROBLEM: 8838
## No 8757 (99.1%)
## Yes 81 (0.92%)
## PRESCRIPTION_MEMORYPROBLEM1: 8831
## No 8658 (98.0%)
## Yes 173 (1.96%)
## DEMENTIA: 8823
## No 8596 (97.4%)
## Yes 227 (2.57%)
## FALLEN: 8823
## No 7089 (80.3%)
## Yes 1734 (19.7%)
## NUMBER TIMES FALLEN 1.12 (7.21) 8837
## FALLEN_injury: 8832
## No 8301 (94.0%)
## Yes 531 (6.01%)
## HIP: 8830
## No 8771 (99.3%)
## Yes 59 (0.67%)
## BIRTHDATE: YEAR 70.5 (10.1) 8839
## FALLENNUM 0.20 (0.40) 8823
## FALLEN_injuryNUM 0.06 (0.24) 8832
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯