# Testing hypothesis for equality of  medians of two 
#independent populations 

#Set working directory
setwd("~/Dropbox/ISI SCB/Data sets")

# read in csv file
hw <-read.csv("hwage.csv", TRUE)

x <- hw$Hourly.Wage[hw$Sector=="Health"]

y <- hw$Hourly.Wage[hw$Sector=="Education"]

#check for outliers
boxplot(x,y)

#assess normality assumptions of x and y
qqnorm(x, ylab = "x Sample Quantiles")
qqnorm(y, ylab = "y Sample Quantiles")

shapiro.test(x)
shapiro.test(y)

#Mann Whitney U test 
#(Wilcoxon test) for medians of 2 independent populations
wilcox.test(x,y, paired=FALSE, conf.int=TRUE)
median(x)
median(y)

#Parametric test
var.test(x,y)
t.test(x,y, alternative="two.sided", var.equal = TRUE)