#part 2
cpsdat<-read.csv("cps2012.csv")
head(cpsdat)

#c)

table(cpsdat$nchlt5)

table1<-table(cpsdat$nchlt5)
table1
round(prop.table(table1),digits = 4)


table2<-table(cpsdat$sex)
table2
round(prop.table(table2),digits = 4)


No.U5<- subset(cpsdat, nchlt5=="No children under age 5")

with(No.U5,table(nchlt5))


table2<-table(No.U5$nchlt5, No.U5$sex)
table2
prop.table(table2)
round(prop.table(table2, margin=1),digits = 4)

#or

No.U5<- cpsdat[cpsdat$nchlt5=="No children under age 5", , drop = FALSE]

#F
chisq.test(factor(cpsdat$educ),factor(cpsdat$race))


###part 3

NJHEALTH<-read.csv("NJHealth1000.csv")
head(NJHEALTH)


smodel<-with(NJHEALTH,lm(avgDrinksPerDay~age))
smodel
summary(smodel)

mmodel<-with(NJHEALTH,lm(avgDrinksPerDay~age+educ))
mmodel
summary(mmodel)