hw4.R

data <- read.csv(file = 'data.csv')
head(data)

##   Applicant.ID Division Gender Hired
## 1            1        E Female     N
## 2            2        A   Male     Y
## 3            3        F   Male     N
## 4            4        F Female     N
## 5            5        E Female     Y
## 6            6        A   Male     Y

summary(data)

##   Applicant.ID  Division    Gender     Hired   
##  Min.   :   1   A:1202   Female:2365   N:3571  
##  1st Qu.:1459   B: 754   Male  :3468   Y:2262  
##  Median :2917   C:1183                         
##  Mean   :2917   D:1022                         
##  3rd Qu.:4375   E: 752                         
##  Max.   :5833   F: 920

str(data)

## 'data.frame':    5833 obs. of  4 variables:
##  $ Applicant.ID: int  1 2 3 4 5 6 7 8 9 10 ...
##  $ Division    : Factor w/ 6 levels "A","B","C","D",..: 5 1 6 6 5 1 3 2 3 6 ...
##  $ Gender      : Factor w/ 2 levels "Female","Male": 1 2 2 1 1 2 1 2 1 1 ...
##  $ Hired       : Factor w/ 2 levels "N","Y": 1 2 1 1 2 2 1 1 1 1 ...

data.tab<-table(data$Gender,data$Hired)
data.tab

##         
##             N    Y
##   Female 1647  718
##   Male   1924 1544

str(data.tab)

##  'table' int [1:2, 1:2] 1647 1924 718 1544
##  - attr(*, "dimnames")=List of 2
##   ..$ : chr [1:2] "Female" "Male"
##   ..$ : chr [1:2] "N" "Y"

head(data.tab)

##         
##             N    Y
##   Female 1647  718
##   Male   1924 1544

addmargins(data.tab,2)

##         
##             N    Y  Sum
##   Female 1647  718 2365
##   Male   1924 1544 3468

prop.table(data.tab,1)

##         
##                  N         Y
##   Female 0.6964059 0.3035941
##   Male   0.5547866 0.4452134

cbind(addmargins(data.tab,2),prop.table(data.tab,1))

##           N    Y  Sum         N         Y
## Female 1647  718 2365 0.6964059 0.3035941
## Male   1924 1544 3468 0.5547866 0.4452134

data2<- xtabs(~Gender + Hired, data=data)
head(data2)

##         Hired
## Gender      N    Y
##   Female 1647  718
##   Male   1924 1544

library(vcd)

## Warning: package 'vcd' was built under R version 3.6.2

## Loading required package: grid

assocstats(data2)

##                     X^2 df P(> X^2)
## Likelihood Ratio 120.39  1        0
## Pearson          118.79  1        0
## 
## Phi-Coefficient   : 0.143 
## Contingency Coeff.: 0.141 
## Cramer's V        : 0.143

summary(data2)

## Call: xtabs(formula = ~Gender + Hired, data = data)
## Number of cases in table: 5833 
## Number of factors: 2 
## Test for independence of all factors:
##  Chisq = 118.79, df = 1, p-value = 1.167e-27