R-blogger Exercise

library(AER)

## Loading required package: car

## Warning: package 'car' was built under R version 3.4.4

## Loading required package: carData

## Warning: package 'carData' was built under R version 3.4.4

## Loading required package: lmtest

## Warning: package 'lmtest' was built under R version 3.4.4

## Loading required package: zoo

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

## Loading required package: sandwich

## Loading required package: survival

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 3.4.4

## -- Attaching packages ---------------------------------- tidyverse 1.2.1 --

## v ggplot2 2.2.1     v purrr   0.2.4
## v tibble  1.4.2     v dplyr   0.7.4
## v tidyr   0.7.2     v stringr 1.2.0
## v readr   1.1.1     v forcats 0.2.0

## Warning: package 'tibble' was built under R version 3.4.4

## Warning: package 'tidyr' was built under R version 3.4.3

## Warning: package 'readr' was built under R version 3.4.3

## Warning: package 'dplyr' was built under R version 3.4.3

## Warning: package 'stringr' was built under R version 3.4.3

## Warning: package 'forcats' was built under R version 3.4.3

## -- Conflicts ------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
## x dplyr::recode() masks car::recode()
## x purrr::some()   masks car::some()

data("CPS1985")
df<-CPS1985
attach(df)

tab<-table(occupation)
tab

## occupation
##     worker  technical   services     office      sales management 
##        156        105         83         97         38         55

hist(log(wage),freq = FALSE)
lines(density(log(wage)),col=4)

tab <- table(sector)
barplot(tab)

pie(tab)

xtabs(~ gender + occupation, data = df)

##         occupation
## gender   worker technical services office sales management
##   male      126        53       34     21    21         34
##   female     30        52       49     76    17         21

plot(gender ~ occupation, data = df)

plot(wage ~ gender, data = df)

by(df$wage,df$gender,mean)

## df$gender: male
## [1] 9.994913
## -------------------------------------------------------- 
## df$gender: female
## [1] 7.878857

tapply(df$wage,df$gender,mean)

##     male   female 
## 9.994913 7.878857

malewage <- subset(df, gender == "male")$wage
femalewage <- subset(df, gender == "female")$wage
length(malewage);length(femalewage)

## [1] 289

## [1] 245

qqplot(malewage, femalewage, xlim = range(df$wage), ylim = range(df$wage), xaxs = "i", yaxs = "i", xlab = "male", ylab = "female")
abline(a=0,b = 1)