dean_dil.df <- read.csv(“Data - Deans Dilemma.csv”)
View(dean_dil.df)
summary(dean_dil.df)
library(psych) describe(dean_dil.df)
summary(dean_dil.df$Salary)
table5 <- prop.table(table(dean_dil.df$Placement_B))*100 round(table5, digits=2)
placed.df<- dean_dil.df[ which(dean_dil.df$Placement_B==‘1’), ] View(placed.df)
summary(placed.df$Salary)
aggregate(placed.df\(Salary, by=list(Gender=placed.df\)Gender), mean)
hist(placed.df$Percent_MBA, main= “MBA performance of placed students”, xlab= “MBA Percentage”, ylab= “Count”, xlim= c(50,80), ylim= c(0,150), breaks = 2, col= “gray” )
notplaced.df<- dean_dil.df[ which(dean_dil.df$Placement_B==‘0’), ] View(notplaced.df)
par(mfrow=c(1,2))
hist(placed.df$Percent_MBA, main= “MBA performance of placed students”, xlab= “MBA Percentage”, ylab= “Count”, xlim= c(50,80), ylim= c(0,150), breaks = 2, col= “gray” )
hist(notplaced.df$Percent_MBA, main= “MBA performance of not placed students”, xlab= “MBA Percentage”, ylab= “Count”, xlim= c(50,80), ylim= c(0,30), breaks = 2, col= “gray” ) par(mfrow=c(1,1))
boxplot(placed.df\(Salary~placed.df\)Gender, horizontal= TRUE, yaxt=“n”, main= “Comparison of Salaries of Males and Females”, xlab= “Salary”, ylab= “Gender” ) axis(side=2, at=c(1,2), labels=c(“Females”, “Males”))
placedET.df<- dean_dil.df[ which(dean_dil.df\(Placement_B=='1'& dean_dil.df\)S.TEST==‘1’ ), ] View(placedET.df)
library(car) scatterplotMatrix(formula= ~ Salary + Percent_MBA + Percentile_ET, cex=1.0, data= placedET.df, main= “Scatter Plot Matrix” ) #16) Run a t-test to test the following hypothesis: #H1: The average salary of the male MBAs is higher than the average salary of female MBAs. t.test(placed.df\(Salary~placed.df\)Gender)