Homework4

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   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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(readxl)
TexasCountyPoverty<-read_excel("TexasCountyPoverty.xlsx")

pastecs::stat.desc(TexasCountyPoverty$pct_decimal)

##      nbr.val     nbr.null       nbr.na          min          max        range 
##   7.00000000   0.00000000   0.00000000   0.10600000   0.27600000   0.17000000 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
##   1.26000000   0.16500000   0.18000000   0.02094210   0.05124347   0.00307000 
##      std.dev     coef.var 
##   0.05540758   0.30781989

The variable shows the percentages of poverty in 7 counties in the state of Texas.

hist(TexasCountyPoverty$pct_decimal,breaks=10)

TexasCountyPoverty<-TexasCountyPoverty %>% mutate(POV_LOG_TRANSFORM=log(pct_decimal))

hist(TexasCountyPoverty$POV_LOG_TRANSFORM)