PAD 6833: HW 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   4.0.0     ✔ 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)
Public_School_Characteristics_2022_23 <- read_csv("Public_School_Characteristics_2022-23.csv")

## Rows: 101390 Columns: 77
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (23): NCESSCH, SURVYEAR, STABR, LEAID, ST_LEAID, LEA_NAME, SCH_NAME, LST...
## dbl (54): X, Y, OBJECTID, STATUS, TOTFRL, FRELCH, REDLCH, DIRECTCERT, PK, KG...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

pastecs::stat.desc(Public_School_Characteristics_2022_23$STUTERATIO)

##       nbr.val      nbr.null        nbr.na           min           max 
##  9.957600e+04  9.800000e+02  1.814000e+03 -2.000000e+00  3.600000e+03 
##         range           sum        median          mean       SE.mean 
##  3.602000e+03  1.493953e+06  1.440000e+01  1.500315e+01  6.986391e-02 
##  CI.mean.0.95           var       std.dev      coef.var 
##  1.369324e-01  4.860270e+02  2.204602e+01  1.469426e+00

The variable described above is the Student to Teacher ratio at various schools surveyed. According to the descriptions above, it looks like the mean student to teacher ratio is 15 students to 1 teacher, while the minimum is -2 (most likely used to signify missing or invalid data) and 3,600 (also possibly missing or invalid data).

new_Public_School_Characteristics_2022_23 <-Public_School_Characteristics_2022_23 |> filter(STUTERATIO>0) |> drop_na(STUTERATIO)

hist(new_Public_School_Characteristics_2022_23$STUTERATIO)

transformed_new_Public_School_Characteristics_2022_23 <-new_Public_School_Characteristics_2022_23 |> mutate(STUTERATIO_log=(STUTERATIO))

hist(transformed_new_Public_School_Characteristics_2022_23$STUTERATIO_log)

hist(log(new_Public_School_Characteristics_2022_23$STUTERATIO))