Homework 4

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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)

#question2: the variable i have selected to measure is number of students enrolled in the texas counties. These variables provide data on the highest and lowest student population in each county.

district_data<-read_excel("district.xls")

stat.desc(district_data$DPETALLC,norm=T)

##      nbr.val     nbr.null       nbr.na          min          max        range 
## 1.207000e+03 0.000000e+00 0.000000e+00 4.000000e+00 1.937270e+05 1.937230e+05 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 5.402928e+06 8.840000e+02 4.476328e+03 3.594000e+02 7.051187e+02 1.559062e+08 
##      std.dev     coef.var     skewness     skew.2SE     kurtosis     kurt.2SE 
## 1.248624e+04 2.789393e+00 6.976469e+00 4.953617e+01 7.077808e+01 2.514855e+02 
##   normtest.W   normtest.p 
## 3.504454e-01 4.578361e-54

summary(district_data$DPETALLC)

##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
##      4.0    337.5    884.0   4476.3   2746.0 193727.0

hist(district_data$DPETALLC)

district_data_transformed<-district_data |> mutate (DPETALLC_log=log(DPETALLC))

hist(district_data_transformed$DPETALLC_log)