DeanDataRevisit

#3d 

dean.df <- read.csv(paste("Data - Deans Dilemma.csv",sep=""))
View(dean.df)

#3d 1
placedstudents.df <- dean.df[which(dean.df$Placement=="Placed"),];
 aggregate( placedstudents.df$Salary,by=list(Gender=placedstudents.df$Gender),mean)

##   Gender        x
## 1      F 253068.0
## 2      M 284241.9

#3d 2

mean(placedstudents.df$Salary[which(placedstudents.df$Gender =="M")],)

## [1] 284241.9

Average salary on male is 284241

#3d 3
mean(placedstudents.df$Salary[which(placedstudents.df$Gender =="F")],)

## [1] 253068

average salary of Female is 253068

#3d 4
t.test(Salary~Gender, placedstudents.df)

## 
##  Welch Two Sample t-test
## 
## data:  Salary by 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:
##  -51138.42 -11209.22
## sample estimates:
## mean in group F mean in group M 
##        253068.0        284241.9

3d 5)p-value = .00234

3d 6)p-value of the test comes to be <0.05 therefore null hypothesis can be rejected that there is not significant difference between salary of male and female