Homework 4

knitr::opts_chunk$set(echo = TRUE)

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(pastecs)

## 
## Attaching package: 'pastecs'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## The following object is masked from 'package:tidyr':
## 
##     extract

library(readxl)
library(car)

## Loading required package: carData
## 
## Attaching package: 'car'
## 
## The following object is masked from 'package:dplyr':
## 
##     recode
## 
## The following object is masked from 'package:purrr':
## 
##     some

library(dplyr)

district <- read_excel("district.xls")

stat.desc(district$DPETECOP, norm = TRUE)

##       nbr.val      nbr.null        nbr.na           min           max 
##  1.207000e+03  4.000000e+00  0.000000e+00  0.000000e+00  1.000000e+02 
##         range           sum        median          mean       SE.mean 
##  1.000000e+02  7.332580e+04  6.190000e+01  6.075046e+01  6.251430e-01 
##  CI.mean.0.95           var       std.dev      coef.var      skewness 
##  1.226489e+00  4.717001e+02  2.171866e+01  3.575061e-01 -4.401852e-01 
##      skew.2SE      kurtosis      kurt.2SE    normtest.W    normtest.p 
## -3.125520e+00 -1.791270e-01 -6.364660e-01  9.796345e-01  5.308455e-12

hist(district$DPETECOP, breaks = 20)

district <- district %>%
  mutate(econ_sqrt = sqrt(DPETECOP))
round(stat.desc(district$econ_sqrt, norm = TRUE), 2)

##      nbr.val     nbr.null       nbr.na          min          max        range 
##      1207.00         4.00         0.00         0.00        10.00        10.00 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
##      9201.04         7.87         7.62         0.05         0.09         2.64 
##      std.dev     coef.var     skewness     skew.2SE     kurtosis     kurt.2SE 
##         1.63         0.21        -1.34        -9.50         2.71         9.63 
##   normtest.W   normtest.p 
##         0.91         0.00

hist(district$econ_sqrt, breaks = 20)