library(readxl)
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
Hot<-read_excel("HOTax.xlsx")
pastecs::stat.desc(Hot$`Advertising Revenue`)
## nbr.val nbr.null nbr.na min max range
## 1.511000e+03 8.900000e+01 8.840000e+02 0.000000e+00 3.951224e+07 3.951224e+07
## sum median mean SE.mean CI.mean.0.95 var
## 7.928100e+08 3.580927e+04 5.246922e+05 6.719031e+04 1.317962e+05 6.821466e+12
## std.dev coef.var
## 2.611794e+06 4.977763e+00
# The variable of interest is "Advertising Revenue". This variable measures the amount of money municipalities allocate for promotional programs to attract visitors.
Hot_Cleaned<-Hot%>%filter(!is.na(`Advertising Revenue`))
hist(Hot_Cleaned$`Advertising Revenue`)

sqrt_y<-sqrt(Hot_Cleaned$`Advertising Revenue`)
mutate(Hot_Cleaned,sqrt_y=Hot_Cleaned$`Advertising Revenue`)
## # A tibble: 1,511 × 21
## `Fiscal Year` `Local Government Type` `Local Government Name` Website
## <dbl> <chr> <chr> <chr>
## 1 2019 city City of Abilene <NA>
## 2 2021 city City of Abilene <NA>
## 3 2020 city City of Abilene <NA>
## 4 2022 city City of Abilene <NA>
## 5 2019 city City of Addison <NA>
## 6 2022 city City of Addison <NA>
## 7 2017 city City of Addison <NA>
## 8 2021 city City of Addison <NA>
## 9 2018 city City of Addison <NA>
## 10 2020 city City of Addison <NA>
## # ℹ 1,501 more rows
## # ℹ 17 more variables: `Tax Code Ch. 351 Rate` <dbl>,
## # `Tax Code Ch. 351 Revenue` <dbl>, `Information Centers Revenue` <dbl>,
## # `Information Centers Percentages` <dbl>, `Registration Revenue` <dbl>,
## # `Registration Percentages` <dbl>, `Advertising Revenue` <dbl>,
## # `Advertising Percentages` <dbl>, `Arts Revenue` <dbl>,
## # `Arts Percentages` <dbl>, `Historical Projects Revenue` <dbl>, …
hist(sqrt_y)
