NHIS Data Skills drill 4

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)

Data Prep

NHIS_DATA<-read.csv("C:/Users/12055/Downloads/SD4 NHIS Data ALT.csv")
NHIS_Data<-NHIS_DATA%>%
  mutate(K6= ifelse(K6>=99, NA,
         ifelse(K6<5,"Low Risk",
                   ifelse(K6>=5 & K6<13,"Moderate Risk", NA 
                   ))),
sexorien= ifelse(sexorien==1,"GayOrLesbian",
                ifelse(sexorien==2,"Straight",
                       ifelse(sexorien==3, "Bisexual",
                              ifelse(sexorien==4, "Other", NA)))),
health= ifelse(health==1, "Excellent",
                        ifelse(health==2, "Very Good",
                ifelse(health==3,"Good",
                        ifelse(health==4,"Fair",NA
                        )))),
 health=factor(health, levels=c("Excellent", "Very Good", "Good", "Fair", "Poor")))%>%
  rename(K6Category= K6) 

Mean K6 Score

NHIS_DATA%>%
  filter(!is.na(health))%>%
 summarize(averageK6=mean(K6))

##   averageK6
## 1  6.266265

Percent health & sexual orientation

NHIS_Data=na.omit(NHIS_Data)

table(NHIS_Data$health)%>%
  prop.table()

## 
## Excellent Very Good      Good      Fair      Poor 
## 0.2728631 0.3398502 0.2811228 0.1061639 0.0000000

table(NHIS_Data$sexorien)%>%
  prop.table()

## 
##     Bisexual GayOrLesbian        Other     Straight 
##  0.008097341  0.016584394  0.002976964  0.972341301