#------------ 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)#Total count of the sample
count(data)## # A tibble: 1 x 1
## n
## <int>
## 1 738#parenthood status
table(data$parenthood)##
## No Yes
## 571 167prop.table(table(data$parenthood))##
## No Yes
## 0.7737127 0.2262873#graduate status
table(data$graduate)#0=undergraduate, 1=graduate##
## 0 1
## 535 203prop.table(table(data$graduate))##
## 0 1
## 0.7249322 0.2750678#parenthood by graduate status
table(data$parenthood, data$graduate)##
## 0 1
## No 445 126
## Yes 90 77prop.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 2203prop.table(wtd.table(data$parenthood,weights = data$finalweight))## No Yes
## 0.8503803 0.1496197wtd.table(data$graduate, weights = data$finalweight)#0=undergraduate, 1=graduate## 0 1
## 12353 2371prop.table(wtd.table(data$graduate, weights = data$finalweight))## 0 1
## 0.8389704 0.1610296wtd.table(data$parenthood, data$graduate, weights = data$finalweight)## 0 1
## No 10949 1572
## Yes 1404 799prop.table(wtd.table(data$parenthood, data$graduate, weights = data$finalweight), margin=2)## 0 1
## No 0.8863434 0.6630114
## Yes 0.1136566 0.3369886#un-weighted
Hmisc::describe(data$res_use_both_mean)## data$res_use_both_mean
## n missing distinct Info Mean Gmd
## 519 219 5 0.755 2.796 0.6127
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 3 152 313 50 1
## Proportion 0.006 0.293 0.603 0.096 0.002t.test(res_use_both_mean~parenthood, data=data, var.equal=TRUE)##
## Two Sample t-test
##
## data: res_use_both_mean by parenthood
## t = -0.22078, df = 517, p-value = 0.8254
## alternative hypothesis: true difference in means between group No and group Yes is not equal to 0
## 95 percent confidence interval:
## -0.1427821 0.1139322
## sample estimates:
## mean in group No mean in group Yes
## 2.792593 2.807018#weighted
Hmisc::describe(data$res_use_both_mean, weights = data$finalweight)## data$res_use_both_mean
## n missing distinct Info Mean
## 10249 4475 5 0.762 2.77
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 95 3122 6086 936 10
## Proportion 0.009 0.305 0.594 0.091 0.001t.test(res_use_both_mean~parenthood, data=data, weights = data$finalweight, var.equal=TRUE)##
## Two Sample t-test
##
## data: res_use_both_mean by parenthood
## t = -0.22078, df = 517, p-value = 0.8254
## alternative hypothesis: true difference in means between group No and group Yes is not equal to 0
## 95 percent confidence interval:
## -0.1427821 0.1139322
## sample estimates:
## mean in group No mean in group Yes
## 2.792593 2.807018##### Social Support #################################################################
#unweighted
Hmisc::describe(data$socialsupport_both_mean)## data$socialsupport_both_mean
## n missing distinct Info Mean Gmd
## 607 131 5 0.878 3.489 0.9084
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 6 63 229 246 63
## Proportion 0.010 0.104 0.377 0.405 0.104t.test(socialsupport_both_mean~parenthood, data=data, 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#weighted
Hmisc::describe(data$socialsupport_both_mean, weights = data$finalweight)## data$socialsupport_both_mean
## n missing distinct Info Mean
## 12375 2349 5 0.881 3.445
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 148 1466 4679 4896 1186
## Proportion 0.012 0.118 0.378 0.396 0.096t.test(socialsupport_both_mean~parenthood, data=data, weights = data$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
#un-weighted
Hmisc::describe(data$academic_diffty_both_mean)## data$academic_diffty_both_mean
## n missing distinct Info Mean Gmd
## 542 196 5 0.899 3.321 1.001
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 7 93 218 167 57
## Proportion 0.013 0.172 0.402 0.308 0.105t.test(academic_diffty_both_mean~parenthood, data=data, 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#weighted
Hmisc::describe(data$academic_diffty_both_mean, weights = data$finalweight)## data$academic_diffty_both_mean
## n missing distinct Info Mean
## 11049 3675 5 0.897 3.381
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 70 1719 4545 3356 1359
## Proportion 0.006 0.156 0.411 0.304 0.123t.test(academic_diffty_both_mean~parenthood, data=data, weights = data$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##### psycsocemo_health_issues ##########################################################
#un-weighted
Hmisc::describe(data$psycsocemo_health_both_mean)## data$psycsocemo_health_both_mean
## n missing distinct Info Mean Gmd
## 557 181 5 0.883 3.578 0.9382
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 1 66 174 242 74
## Proportion 0.002 0.118 0.312 0.434 0.133t.test(psycsocemo_health_both_mean~parenthood, data=data, 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#weighted
Hmisc::describe(data$psycsocemo_health_both_mean, weights = data$finalweight)## data$psycsocemo_health_both_mean
## n missing distinct Info Mean
## 11361 3363 5 0.888 3.592
##
## lowest : 1 2 3 4 5, highest: 1 2 3 4 5
##
## Value 1 2 3 4 5
## Frequency 42 1343 3469 4866 1641
## Proportion 0.004 0.118 0.305 0.428 0.144t.test(psycsocemo_health_both_mean~parenthood, data=data, weights = data$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 3.390476data$parenthood<-as.factor(data$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)
reg_psycsocemo_health_both<-lm(psycsocemo_health_both_mean~agegroup + + binary_gender + race3 + graduate + parenthood, data=data, weights = data$finalweight, var.equal=TRUE)
summary(reg_psycsocemo_health_both)##
## Call:
## lm(formula = psycsocemo_health_both_mean ~ agegroup + +binary_gender +
## race3 + graduate + parenthood, data = data, weights = data$finalweight,
## var.equal = TRUE)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -15.5852 -2.7466 0.7182 2.0269 10.3377
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.06097 0.13546 29.979 < 2e-16 ***
## agegroup2 0.18824 0.09707 1.939 0.052985 .
## agegroup3 0.01052 0.10646 0.099 0.921337
## agegroup4 0.12519 0.15440 0.811 0.417796
## binary_gender2 -0.19123 0.07473 -2.559 0.010769 *
## race31 -0.23218 0.26166 -0.887 0.375280
## race32 -0.54721 0.14542 -3.763 0.000186 ***
## race33 0.07585 0.19001 0.399 0.689927
## race34 -0.47540 0.12579 -3.779 0.000174 ***
## graduate1 -0.27379 0.12409 -2.206 0.027782 *
## parenthoodYes -0.20306 0.15018 -1.352 0.176912
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.884 on 546 degrees of freedom
## (181 observations deleted due to missingness)
## Multiple R-squared: 0.08108, Adjusted R-squared: 0.06425
## F-statistic: 4.817 on 10 and 546 DF, p-value: 1.164e-06