#------------ setwd
setwd("C:/Users/C00252837/Dropbox/StudentParentsData")
#------------Read in Data
data<-read.csv("sutdentparents_survey_weighted.csv", header = T)
data<-as_tibble(data)
names(data)
## [1] "ï..Column1" "x1"
## [3] "Ã.Column1" "x"
## [5] "classification" "enrollment"
## [7] "department" "q4"
## [9] "finanacial_assistance" "q24_8_text"
## [11] "q23" "q38"
## [13] "q5" "q43"
## [15] "employment_status" "gender"
## [17] "gender2" "q10_5_text"
## [19] "age_original" "race"
## [21] "race2" "q46"
## [23] "q46_4_text" "q47"
## [25] "q47_11_text" "pregnancy"
## [27] "parenthood" "numb_children"
## [29] "age_children" "q35_13"
## [31] "q35_14" "q35_15"
## [33] "q62" "column226"
## [35] "res_aware_both_mean" "res_aware_patuniq_mean"
## [37] "res_use_both_mean" "res_use_patuniq_mean"
## [39] "socialsupport_both_mean" "socialsupport_patuniq_mean"
## [41] "positive_exp_both_mean" "positive_exp_patuniq_mean"
## [43] "negative_exp_gen_both_mean" "negative_exp_gen_patuniq_mean"
## [45] "academic_diffty_both_mean" "academic_diffty_patuniq_mean"
## [47] "financial_ins_both_mean" "financial_ins_patuniq_mean"
## [49] "housing_ins_both_mean" "physical_health_both_mean"
## [51] "psycsocemo_health_both_mean" "psycsocemo_health_patuniq_mean"
## [53] "expectations_both_mean" "expectations_patuniq_mean"
## [55] "pat_childcare_patuniq_mean" "child_issues_patuniq_mean"
## [57] "pregnancy_patuniq_mean" "age_recoded"
## [59] "age_recoded_narm" "parenthood_age"
## [61] "parenthood_age_narm" "res_aware_both_mean_recode"
## [63] "res_use_both_mean_recode" "socialsupport_both_mean_recode"
## [65] "positive_exp_both_mean_recode" "negative_exp_gen_both_mean_recod"
## [67] "academic_diffty_both_mean_recode" "financial_ins_both_mean_recode"
## [69] "housing_ins_both_mean_recode" "physical_health_both_mean_recode"
## [71] "psycsocemo_health_both_mean_reco" "nurs_or_not"
## [73] "age" "agegroup"
## [75] "binary_gender_original" "binary_gender"
## [77] "race3" "graduate"
## [79] "agegroup_tot" "binary_gender_tot"
## [81] "race3_tot" "graduate_tot"
## [83] "counter1" "sample_tot"
## [85] "baseweight" "finalweight"
data <- data%>%
rename(
ID = x)
Complex Survey Analysis
#Total count of the sample
count(data)
## # A tibble: 1 x 1
## n
## <int>
## 1 738
#parenthood status
table(data$parenthood)
##
## No Yes
## 571 167
prop.table(table(data$parenthood))
##
## No Yes
## 0.7737127 0.2262873
#graduate status
table(data$graduate)#0=undergraduate, 1=graduate
##
## 0 1
## 535 203
prop.table(table(data$graduate))
##
## 0 1
## 0.7249322 0.2750678
#parenthood by graduate status
table(data$parenthood, data$graduate)
##
## 0 1
## No 445 126
## Yes 90 77
prop.table(table(data$parenthood, data$graduate), margin=2)
##
## 0 1
## No 0.8317757 0.6206897
## Yes 0.1682243 0.3793103
Create a survey design object
Use functions in a new library, called survey
library(survey)
des<-svydesign(ids=~1, weights=~finalweight, data = data)
#re-do the analysis from above using sample weights
library(questionr)
wtd.table(data$parenthood,weights = data$finalweight)
## No Yes
## 12521 2203
prop.table(wtd.table(data$parenthood,weights = data$finalweight))
## No Yes
## 0.8503803 0.1496197
wtd.table(data$graduate, weights = data$finalweight)#0=undergraduate, 1=graduate
## 0 1
## 12353 2371
prop.table(wtd.table(data$graduate, weights = data$finalweight))
## 0 1
## 0.8389704 0.1610296
wtd.table(data$parenthood, data$graduate, weights = data$finalweight)
## 0 1
## No 10949 1572
## Yes 1404 799
prop.table(wtd.table(data$parenthood, data$graduate, weights = data$finalweight), margin=2)
## 0 1
## No 0.8863434 0.6630114
## Yes 0.1136566 0.3369886
Codes in the weighted data file
parenthood=Yes (parents),parenthood=No(non-parents)
agegroup=1(age<20), agegroup=2(age>=20 & age<22),agegroup=3 (age>=22 & age<25),agegroup=4 (age>=25 & age!=.)
binary_gender=1 (Female),binary_gender=2 (Male
race3=0(Other),race3=1(Asian),race3=2(Black or African American),race3=3(Hispanic or Latino or Spanish origin of any race),race3=4 (White or Caucasian)
graduate=0(undergraduate),graduate=1(graduate)
data$parenthood<-as.factor(data$parenthood)
data$agegroup<-as.factor(data$agegroup)
data$binary_gender<-as.factor(data$binary_gender)#1=female, 2=male
data$race3<-as.factor(data$race3)
data$graduate<-as.factor(data$graduate)
t-tests (comparing parents against non-parents)
Social Support
###################### Social Support #################################################################
#weighted
Hmisc::describe(data$socialsupport_both_mean, weights = data$finalweight)
## data$socialsupport_both_mean
## n missing distinct Info Mean
## 12375 2349 5 0.881 3.445
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 148 1466 4679 4896 1186
## Proportion 0.012 0.118 0.378 0.396 0.096
t.test(socialsupport_both_mean~parenthood, data=data, weights = data$finalweight, var.equal=TRUE)
##
## Two Sample t-test
##
## data: socialsupport_both_mean by parenthood
## t = -2.8398, df = 605, p-value = 0.004665
## alternative hypothesis: true difference in means between group No and group Yes is not equal to 0
## 95 percent confidence interval:
## -0.4107835 -0.0749049
## sample estimates:
## mean in group No mean in group Yes
## 3.440083 3.682927
Academic Difficulty
###################### academic_difficulty ##########################################################
#weighted
Hmisc::describe(data$academic_diffty_both_mean, weights = data$finalweight)
## data$academic_diffty_both_mean
## n missing distinct Info Mean
## 11049 3675 5 0.897 3.381
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 70 1719 4545 3356 1359
## Proportion 0.006 0.156 0.411 0.304 0.123
t.test(academic_diffty_both_mean~parenthood, data=data, weights = data$finalweight, var.equal=TRUE)
##
## Two Sample t-test
##
## data: academic_diffty_both_mean by parenthood
## t = 3.0432, df = 540, p-value = 0.002454
## alternative hypothesis: true difference in means between group No and group Yes is not equal to 0
## 95 percent confidence interval:
## 0.1058207 0.4911664
## sample estimates:
## mean in group No mean in group Yes
## 3.381062 3.082569
Psychosocioemotional Health Issues
###################### psycsocemo_health_issues ##########################################################
#weighted
Hmisc::describe(data$psycsocemo_health_both_mean, weights = data$finalweight)
## data$psycsocemo_health_both_mean
## n missing distinct Info Mean
## 11361 3363 5 0.888 3.592
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 42 1343 3469 4866 1641
## Proportion 0.004 0.118 0.305 0.428 0.144
t.test(psycsocemo_health_both_mean~parenthood, data=data, weights = data$finalweight, var.equal=TRUE)
##
## Two Sample t-test
##
## data: psycsocemo_health_both_mean by parenthood
## t = 2.4613, df = 555, p-value = 0.01415
## alternative hypothesis: true difference in means between group No and group Yes is not equal to 0
## 95 percent confidence interval:
## 0.04668813 0.41572232
## sample estimates:
## mean in group No mean in group Yes
## 3.621681 3.390476
Multiple Regression Analysisz
Predicting psychosocioemotional health issues
reg_psycsocemo_health_both<-lm(psycsocemo_health_both_mean~age + + binary_gender + race3 + graduate + parenthood + socialsupport_both_mean + financial_ins_both_mean + physical_health_both_mean+negative_exp_gen_both_mean+res_aware_both_mean+res_use_both_mean, data=data,weights = data$finalweight, var.equal=TRUE)
summary(reg_psycsocemo_health_both)
##
## Call:
## lm(formula = psycsocemo_health_both_mean ~ age + +binary_gender +
## race3 + graduate + parenthood + socialsupport_both_mean +
## financial_ins_both_mean + physical_health_both_mean + negative_exp_gen_both_mean +
## res_aware_both_mean + res_use_both_mean, data = data, weights = data$finalweight,
## var.equal = TRUE)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -9.7646 -1.4429 0.1523 1.5828 10.8534
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.340462 0.305788 7.654 1.44e-13 ***
## age 0.009717 0.004898 1.984 0.047956 *
## binary_gender2 -0.031942 0.058456 -0.546 0.585069
## race31 -0.224753 0.194028 -1.158 0.247402
## race32 -0.312628 0.120877 -2.586 0.010048 *
## race33 0.110757 0.151485 0.731 0.465116
## race34 -0.177643 0.108040 -1.644 0.100904
## graduate1 -0.183319 0.089324 -2.052 0.040783 *
## parenthoodYes -0.153778 0.104915 -1.466 0.143496
## socialsupport_both_mean -0.194628 0.039873 -4.881 1.52e-06 ***
## financial_ins_both_mean 0.080372 0.040212 1.999 0.046309 *
## physical_health_both_mean 0.113511 0.031607 3.591 0.000369 ***
## negative_exp_gen_both_mean 0.351640 0.037877 9.284 < 2e-16 ***
## res_aware_both_mean -0.076619 0.034335 -2.232 0.026193 *
## res_use_both_mean 0.078480 0.049987 1.570 0.117193
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.584 on 405 degrees of freedom
## (318 observations deleted due to missingness)
## Multiple R-squared: 0.5598, Adjusted R-squared: 0.5446
## F-statistic: 36.79 on 14 and 405 DF, p-value: < 2.2e-16
Predicting academic difficulty
reg_academic_diffty_both_mean<-lm(academic_diffty_both_mean~age + binary_gender + race3 + graduate + parenthood + socialsupport_both_mean + financial_ins_both_mean + physical_health_both_mean + psycsocemo_health_both_mean +negative_exp_gen_both_mean+res_aware_both_mean+res_use_both_mean, data=data, weights = data$finalweight, var.equal=TRUE)
summary(reg_academic_diffty_both_mean)
##
## Call:
## lm(formula = academic_diffty_both_mean ~ age + binary_gender +
## race3 + graduate + parenthood + socialsupport_both_mean +
## financial_ins_both_mean + physical_health_both_mean + psycsocemo_health_both_mean +
## negative_exp_gen_both_mean + res_aware_both_mean + res_use_both_mean,
## data = data, weights = data$finalweight, var.equal = TRUE)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -8.9572 -1.5377 0.0451 1.5860 8.3100
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.030413 0.337804 3.050 0.002445 **
## age 0.003766 0.005134 0.734 0.463635
## binary_gender2 0.188868 0.059949 3.150 0.001758 **
## race31 -0.049806 0.197089 -0.253 0.800627
## race32 -0.244506 0.127229 -1.922 0.055374 .
## race33 -0.068956 0.160077 -0.431 0.666878
## race34 -0.347905 0.113466 -3.066 0.002322 **
## graduate1 -0.191759 0.092668 -2.069 0.039186 *
## parenthoodYes -0.027261 0.106857 -0.255 0.798766
## socialsupport_both_mean -0.038395 0.042218 -0.909 0.363687
## financial_ins_both_mean 0.277161 0.041316 6.708 7.07e-11 ***
## physical_health_both_mean -0.002769 0.032802 -0.084 0.932770
## psycsocemo_health_both_mean 0.179274 0.050813 3.528 0.000469 ***
## negative_exp_gen_both_mean 0.292907 0.042470 6.897 2.20e-11 ***
## res_aware_both_mean -0.089898 0.035379 -2.541 0.011446 *
## res_use_both_mean 0.102530 0.051325 1.998 0.046460 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.59 on 384 degrees of freedom
## (338 observations deleted due to missingness)
## Multiple R-squared: 0.5927, Adjusted R-squared: 0.5768
## F-statistic: 37.25 on 15 and 384 DF, p-value: < 2.2e-16
Social Support