Dean’s Dilemma continued

mydata <- read.csv(file = "Data - Deans Dilemma.csv", sep = ",")
placed <- mydata[which(mydata$Placement_B == 1),]

MEAN SALARY OF MEN AND WOMEN

placed$Gender = factor(placed$Gender, levels = c("M","F"), labels = c("Male","Female"))
aggregate(placed$Salary,by = list(Gender = placed$Gender),mean)

##   Gender        x
## 1   Male 284241.9
## 2 Female 253068.0

T-Test

t.test(placed$Salary~placed$Gender,data = placed)

## 
##  Welch Two Sample t-test
## 
## data:  placed$Salary by placed$Gender
## t = 3.0757, df = 243.03, p-value = 0.00234
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  11209.22 51138.42
## sample estimates:
##   mean in group Male mean in group Female 
##             284241.9             253068.0

Hence, we can reject the hypothesis that the average salary of males and females is equal since p<0.01 As seen above, p-value=0.00234

AVERAGE SALARY OF MALES

mytable<-placed[which(placed$Gender.B=="0"),]
m.sal<-mean(mytable$Salary)
m.sal

## [1] 284241.9

AVERAGE SALARY OF FEMALES

mytable2<-placed[which(placed$Gender.B=="1"),]
f.sal<-mean(mytable2$Salary)
f.sal

## [1] 253068