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(readxl)
library(pastecs)
## 
## Attaching package: 'pastecs'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## The following object is masked from 'package:tidyr':
## 
##     extract
texas_counties <- read_excel("tx.counties.xlsx", sheet = "Additional Measure Data", skip = 1)
## New names:
## • `95% CI - Low` -> `95% CI - Low...5`
## • `95% CI - High` -> `95% CI - High...6`
## • `# Deaths` -> `# Deaths...28`
## • `95% CI - Low` -> `95% CI - Low...30`
## • `95% CI - High` -> `95% CI - High...31`
## • `# Deaths` -> `# Deaths...53`
## • `95% CI - Low` -> `95% CI - Low...55`
## • `95% CI - High` -> `95% CI - High...56`
## • `# Deaths` -> `# Deaths...78`
## • `95% CI - Low` -> `95% CI - Low...80`
## • `95% CI - High` -> `95% CI - High...81`
## • `95% CI - Low` -> `95% CI - Low...104`
## • `95% CI - High` -> `95% CI - High...105`
## • `95% CI - Low` -> `95% CI - Low...107`
## • `95% CI - High` -> `95% CI - High...108`
## • `95% CI - Low` -> `95% CI - Low...112`
## • `95% CI - High` -> `95% CI - High...113`
## • `95% CI - Low` -> `95% CI - Low...115`
## • `95% CI - High` -> `95% CI - High...116`
## • `# Deaths` -> `# Deaths...117`
## • `95% CI - Low` -> `95% CI - Low...119`
## • `95% CI - High` -> `95% CI - High...120`
## • `95% CI - Low` -> `95% CI - Low...144`
## • `95% CI - High` -> `95% CI - High...145`
## • `95% CI - Low` -> `95% CI - Low...151`
## • `95% CI - High` -> `95% CI - High...152`
## • `95% CI - Low` -> `95% CI - Low...154`
## • `95% CI - High` -> `95% CI - High...155`
## • `95% CI - Low` -> `95% CI - Low...180`
## • `95% CI - High` -> `95% CI - High...181`
## • `95% CI - Low` -> `95% CI - Low...185`
## • `95% CI - High` -> `95% CI - High...186`
## • `95% CI - Low` -> `95% CI - Low...189`
## • `95% CI - High` -> `95% CI - High...190`
## • `95% CI - Low` -> `95% CI - Low...213`
## • `95% CI - High` -> `95% CI - High...214`
## • `95% CI - Low` -> `95% CI - Low...216`
## • `95% CI - High` -> `95% CI - High...217`
## • `95% CI - Low` -> `95% CI - Low...220`
## • `95% CI - High` -> `95% CI - High...221`
## • `95% CI - Low` -> `95% CI - Low...224`
## • `95% CI - High` -> `95% CI - High...225`
## • `95% CI - Low` -> `95% CI - Low...231`
## • `95% CI - High` -> `95% CI - High...232`
## • `95% CI - Low` -> `95% CI - Low...235`
## • `95% CI - High` -> `95% CI - High...236`
## • `Average Grade Performance` -> `Average Grade Performance...246`
## • `Average Grade Performance (AIAN)` -> `Average Grade Performance
##   (AIAN)...247`
## • `Average Grade Performance (Asian)` -> `Average Grade Performance
##   (Asian)...248`
## • `Average Grade Performance (Black)` -> `Average Grade Performance
##   (Black)...249`
## • `Average Grade Performance (Hispanic)` -> `Average Grade Performance
##   (Hispanic)...250`
## • `Average Grade Performance (White)` -> `Average Grade Performance
##   (White)...251`
## • `Average Grade Performance` -> `Average Grade Performance...252`
## • `Average Grade Performance (AIAN)` -> `Average Grade Performance
##   (AIAN)...253`
## • `Average Grade Performance (Asian)` -> `Average Grade Performance
##   (Asian)...254`
## • `Average Grade Performance (Black)` -> `Average Grade Performance
##   (Black)...255`
## • `Average Grade Performance (Hispanic)` -> `Average Grade Performance
##   (Hispanic)...256`
## • `Average Grade Performance (White)` -> `Average Grade Performance
##   (White)...257`
## • `Segregation Index` -> `Segregation Index...258`
## • `95% CI - Low` -> `95% CI - Low...265`
## • `95% CI - High` -> `95% CI - High...266`
## • `95% CI - Low` -> `95% CI - Low...268`
## • `95% CI - High` -> `95% CI - High...269`
## • `Segregation Index` -> `Segregation Index...287`
## • `95% CI - Low` -> `95% CI - Low...289`
## • `95% CI - High` -> `95% CI - High...290`
## • `95% CI - Low` -> `95% CI - Low...314`
## • `95% CI - High` -> `95% CI - High...315`
## • `95% CI - Low` -> `95% CI - Low...339`
## • `95% CI - High` -> `95% CI - High...340`
## • `95% CI - Low` -> `95% CI - Low...363`
## • `95% CI - High` -> `95% CI - High...364`
## • `95% CI - Low` -> `95% CI - Low...366`
## • `95% CI - High` -> `95% CI - High...367`
## • `95% CI - Low` -> `95% CI - Low...386`
## • `95% CI - High` -> `95% CI - High...387`
## • `95% CI - Low` -> `95% CI - Low...391`
## • `95% CI - High` -> `95% CI - High...392`
view(data)
food_data <- texas_counties %>% drop_na('% Food Insecure')
food_data <- texas_counties |> drop_na('% Food Insecure')  %>% filter(`% Food Insecure` > 0)
pastecs::stat.desc(food_data$`% Food Insecure`)
##      nbr.val     nbr.null       nbr.na          min          max        range 
##  255.0000000    0.0000000    0.0000000   10.6000000   28.5000000   17.9000000 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 4412.6000000   16.9000000   17.3043137    0.1878593    0.3699602    8.9992333 
##      std.dev     coef.var 
##    2.9998722    0.1733598

the variable i chose for this assignment is % of food insecurity. measures the estimated % of people in each Texas county who did not have reliable access to enough nutricious food during the year 2025.

hist(food_data$'% Food Insecure', main="Food Insecurity Across Texas Counties", xlab="Percentage Food Insecure")

food_data_log <- food_data %>% mutate(LOG_FOOD_INSECURE = log(`% Food Insecure`)) %>% select(`% Food Insecure`, LOG_FOOD_INSECURE)

head(food_data_log)
## # A tibble: 6 × 2
##   `% Food Insecure` LOG_FOOD_INSECURE
##               <dbl>             <dbl>
## 1              16.4              2.80
## 2              16.6              2.81
## 3              15.5              2.74
## 4              18.7              2.93
## 5              19                2.94
## 6              16                2.77

1st 6 counties

hist(food_data_log$LOG_FOOD_INSECURE)

hist(food_data_log$LOG_FOOD_INSECURE, main = "Log-Transformed Food Insecurity", xlab = "Log of Percentage Food Insecure")