Blog Post Two, Descriptive Statistics

Data

library(haven)
setwd("C:/Users/spara/OneDrive/Desktop/project")

ddi <- read_ipums_ddi("C:/Users/spara/OneDrive/Desktop/project/nhis_00006.xml")
data <- read_ipums_micro(ddi)

## Use of data from IPUMS NHIS is subject to conditions including that users
## should cite the data appropriately. Use command `ipums_conditions()` for more
## details.

data<- haven::zap_labels(data)

names(data) <- tolower(gsub(pattern = "_",replacement =  "",x =  names(data)))

Recode the variables

#depression level
data$depfeelevl<-as.factor(data$depfeelevl)
data$depfeelevl<- car::Recode(data$depfeelevl,
                       recodes="1='ALot'; 2='A Little'; 
                       3='Between a Little and a Lot'; 7:9=NA; else=NA",
                      as.factor=T)


# medication for depression
data$deprx <- as.factor(data$deprx)

data$deprx<- car::Recode(data$deprx,
                       recodes="1='No'; 2='Yes';else=NA",
                       as.factor=T)



#currently Pregnant 
data$pregnantnow<-as.factor(data$pregnantnow)
data$curpreg<-car::Recode(data$pregnantnow,
                          recodes="0='Yes';else=NA",
                          as.factor=T)
        
#education level
data$educ<-as.factor(data$educ)
data$educ<-Recode(data$educ,
                        recodes="102 ='NoSchool'; 201='HS Diploma'; 301='Some college'; 
                       400= 'Undergrad'; 501= 'Masters';else=NA", as.factor = T)

#employment status

data$empstat<- car::Recode(data$empstat,
                       recodes="100='Employed'; 200='Unemployed';else=NA",
                       as.factor=T)


##race/ethnicity
data$race<- car::Recode(data$racea,
                       recodes="100 ='White'; 200 ='African American'; 
                       400:434= 'Asian'; 500:590 = 'Other'; else=NA", 
                       as.factor=T)

## marital status
data$mars<- car::Recode(data$marstat, 
                        recodes ="10:13='Married'; 20='Widowed'; 30='Divorced'; 
                        40='Separated'; 50='Never Married'; else=NA", 
                        as.factor=T)

Filter data

data<-data%>%
  filter(is.na(curpreg)==F)
data<-data%>%
  filter(is.na(educ)==F)
data<-data%>%
  filter(is.na(deprx)==F)
data<-data%>%
  filter(is.na(depfeelevl)==F)
data<-data%>%
  filter(is.na(empstat)==F)
data<-data%>%
  filter(is.na(race)==F)
data<-data%>%
  filter(is.na(mars)==F)

Survey design

#First we tell R our survey design
options(survey.lonely.psu = "adjust")

library(dplyr)
sub<-data%>%
  select(depfeelevl, curpreg, educ, deprx, empstat, race, mars, sampweight,strata) %>%
  filter( complete.cases(.))


#First we tell R our survey design

options(survey.lonely.psu = "adjust")
des<-svydesign(ids=~1,
               strata=~strata,
               weights=~sampweight,
               data =sub)

## count education frequency
countedu <- sub %>% 
  group_by(educ)%>%
dplyr::summarise(numedu=n())
countedu

## count employment frequency
countemp <- sub %>% 
  group_by(empstat)%>%
dplyr::summarise(numemp=n())
countemp

## count marital status frequency
countmar <- sub %>% 
  group_by(mars)%>%
dplyr::summarise(nummar=n())
countmar

label(data$depfeelevl) <- "Depression Level"
label(data$deprx) <- "Medication for Depression"
label(data$pregnantnow) <-"Currently Pregnant"
label(data$educ) <- "Education Level"
label(data$empstat)<- "Employment Status"
label(data$race)<- "Race"
label(data$mars)<- "Marital Status"

Results

## Table 1: Demographic properties of currently pregnant women who are either taking or not taking prescription medication for depression
table<-table1(~ educ + empstat + race + mars + depfeelevl | deprx, data=sub)
table

	No (N=11123)	Yes (N=3535)	Overall (N=14658)
educ
HS Diploma	3431 (30.8%)	1195 (33.8%)	4626 (31.6%)
Masters	1628 (14.6%)	490 (13.9%)	2118 (14.4%)
NoSchool	24 (0.2%)	10 (0.3%)	34 (0.2%)
Some college	2614 (23.5%)	893 (25.3%)	3507 (23.9%)
Undergrad	3426 (30.8%)	947 (26.8%)	4373 (29.8%)
empstat
Employed	5739 (51.6%)	1236 (35.0%)	6975 (47.6%)
Unemployed	5384 (48.4%)	2299 (65.0%)	7683 (52.4%)
race
African American	1111 (10.0%)	236 (6.7%)	1347 (9.2%)
Asian	567 (5.1%)	60 (1.7%)	627 (4.3%)
Other	122 (1.1%)	15 (0.4%)	137 (0.9%)
White	9323 (83.8%)	3224 (91.2%)	12547 (85.6%)
mars
Divorced	2066 (18.6%)	853 (24.1%)	2919 (19.9%)
Married	4712 (42.4%)	1433 (40.5%)	6145 (41.9%)
Never Married	2796 (25.1%)	645 (18.2%)	3441 (23.5%)
Separated	164 (1.5%)	56 (1.6%)	220 (1.5%)
Widowed	1385 (12.5%)	548 (15.5%)	1933 (13.2%)
depfeelevl
A Little	878 (7.9%)	833 (23.6%)	1711 (11.7%)
ALot	6651 (59.8%)	1201 (34.0%)	7852 (53.6%)
Between a Little and a Lot	3594 (32.3%)	1501 (42.5%)	5095 (34.8%)

## Figure 1: Depression Among Currently Pregnant Women by Education
Fig1 <- ggplot(data = sub, aes(x=educ, fill=deprx)) + 
  geom_bar(position='fill')+
    geom_text(data=countedu, 
            aes(x=educ, y=0.05, label=numedu), 
            size=5, colour="white", inherit.aes=FALSE)+
labs(title="Depression Among Currently pregnant women 
     by Education", 
         x="Education", y = "Population Proportion", fill ="Legend")+
  theme(legend.position="right")
Fig1

## Figure 2: Depression Among Currently Pregnant Women by Employment Status
Fig2 <- ggplot(data = sub, aes(x=empstat, fill=deprx)) + 
  geom_bar(position='fill')+
  geom_text(data=countemp, 
            aes(x=empstat, y=0.05, label=numemp), 
            size=5, colour="white", inherit.aes=FALSE)+
  labs(title="Depression Among Currently pregnant women by Employment Status", 
         x="Employment", y = "Population Proportion", fill ="Legend")+
  theme(legend.position="right")
Fig2

# Figure 3: Depression Among Currently Pregnant Women by Marital Status
Fig3 <- ggplot(data = sub, aes(x=mars, fill=deprx)) + 
  geom_bar(position='fill')+
  geom_text(data=countmar, 
            aes(x=mars, y=0.05, label=nummar), 
            size=5, colour="white", inherit.aes=FALSE)+
  labs(title="Depression Among Currently pregnant women by Marital Status", 
         x="Marital Status", y = "Population Proportion", fill ="Legend")+
  theme(legend.position="right")
Fig3