Data Dictionary:
DPETECOP -> STUDENTS: % ECONOMICALLY DISADVANTAGED DA0912DR21R -> ANNUAL DROPOUT RATE GR. 9-12 DA0CC21R-> COLLEGE ADMISSIONS: % AT/ABOVE CRITERION DA0AT21R -> ATTENDANCE RATE

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)
bexar_schools<-read.csv("bexar_schools.csv")
bexar_schools_clean<-bexar_schools%>%filter(!is.na(DPETECOP),!is.na(DA0AT21R),!is.na(DA0912DR21R),!is.na(DA0CC21R))
summary(bexar_schools_clean)
##    DISTNAME            DISTRICT       DZCNTYNM             REGION  
##  Length:29          Min.   :15802   Length:29          Min.   :20  
##  Class :character   1st Qu.:15827   Class :character   1st Qu.:20  
##  Mode  :character   Median :15901   Mode  :character   Median :20  
##                     Mean   :15867                      Mean   :20  
##                     3rd Qu.:15910                      3rd Qu.:20  
##                     Max.   :15917                      Max.   :20  
##    DZRATING            DPETECOP        DA0AT21R      DA0912DR21R   
##  Length:29          Min.   : 3.70   Min.   :81.40   Min.   :0.000  
##  Class :character   1st Qu.:48.90   1st Qu.:92.50   1st Qu.:0.000  
##  Mode  :character   Median :68.70   Median :95.10   Median :0.800  
##                     Mean   :62.82   Mean   :94.07   Mean   :1.593  
##                     3rd Qu.:86.10   3rd Qu.:97.30   3rd Qu.:2.700  
##                     Max.   :90.30   Max.   :98.90   Max.   :5.200  
##     DA0CC21R    
##  Min.   :-1.00  
##  1st Qu.:11.60  
##  Median :19.40  
##  Mean   :26.67  
##  3rd Qu.:35.00  
##  Max.   :97.70
head(bexar_schools_clean)
##                             DISTNAME DISTRICT  DZCNTYNM REGION DZRATING
## 1              GEORGE GERVIN ACADEMY    15802 015 BEXAR     20        B
## 2   NEW FRONTIERS PUBLIC SCHOOLS INC    15805 015 BEXAR     20        A
## 3 LEGACY TRADITIONAL SCHOOLS - TEXAS    15806 015 BEXAR     20        C
## 4       SOUTHWEST PREPARATORY SCHOOL    15807 015 BEXAR     20        B
## 5                  INSPIRE ACADEMIES    15808 015 BEXAR     20        B
## 6                   HERITAGE ACADEMY    15815 015 BEXAR     20        A
##   DPETECOP DA0AT21R DA0912DR21R DA0CC21R
## 1     86.7     92.8         0.0      0.0
## 2     73.8     93.8         0.0     25.0
## 3     90.1     90.0         2.1     -1.0
## 4     82.5     90.2         4.1     19.4
## 5     60.2     92.5         0.6     12.5
## 6     79.9     97.3         0.0      7.9
hist(bexar_schools$DPETECOP)

hist(bexar_schools$DA0AT21R)

hist(bexar_schools$DA0912DR21R)

hist(bexar_schools$DA0CC21R)

hist(bexar_schools_clean$DPETECOP, 
     main="Histogram of Economically Disadvantaged Students",
     xlab="Percentage of Economically Disadvantaged Students")

hist(bexar_schools_clean$DA0AT21R, 
     main="Histogram of Attendance Rates",
     xlab="Attendance Rate (%)")

hist(bexar_schools_clean$DA0912DR21R, 
     main="Histogram of Dropout Rates",
     xlab="Dropout Rate (%)")

hist(bexar_schools_clean$DA0CC21R, 
     main="Histogram of College Readiness",
     xlab="College Readiness (%)")

plot(bexar_schools_clean$DPETECOP, bexar_schools_clean$DA0CC21R,
     main = "Economically Disadvantaged vs. College Readiness",
     xlab = "Economically Disadvantaged (%)",
     ylab = "College Readiness (%)")

plot(bexar_schools_clean$DA0AT21R, bexar_schools_clean$DA0912DR21R,
     main = "Attendance Rate vs. Dropout Rate",
     xlab = "Attendance Rate (%)",
     ylab = "Dropout Rate (%)")

plot(bexar_schools_clean$DPETECOP, bexar_schools_clean$DA0AT21R,
     main = "Economically Disadvantaged vs. Attendance Rate",
     xlab = "Economically Disadvantaged (%)",
     ylab = "Attendance Rate (%)")

plot(bexar_schools_clean$DA0912DR21R, bexar_schools_clean$DA0CC21R,
     main = "Dropout Rate vs. College Readiness",
     xlab = "Dropout Rate (%)",
     ylab = "College Readiness (%)")

# Correlation between  Economically Disadvantaged and Colleg readiness
cor(bexar_schools_clean$DPETECOP, bexar_schools_clean$DA0CC21R)
## [1] -0.7557066
# Correlation between Attendance Rate and Dropout Rate
 cor(bexar_schools_clean$DA0AT21R, bexar_schools_clean$DA0912DR21R)
## [1] -0.6772017
# Correlation between Economically Disadvantaged and Attendance Rate
cor(bexar_schools_clean$DPETECOP, bexar_schools_clean$DA0AT21R)
## [1] -0.3891103
# Correlation between Dropout Rate and College Readiness
cor(bexar_schools_clean$DA0912DR21R, bexar_schools_clean$DA0CC21R)
## [1] -0.3009042

Correlation between Economically Disadvantaged and College Readiness: -0.756 This strong negative correlation suggests that as the percentage of economically disadvantaged students increases, college readiness tends to decrease significantly.

Correlation between Attendance Rate and Dropout Rate: -0.677 The moderately strong negative correlation indicates that higher attendance rates are associated with lower dropout rates and suggests that improving school attendance might be an effective strategy for reducing dropout rates.

Correlation between Economically Disadvantaged and Attendance Rate: -0.389 The moderate negative correlation suggests that schools with higher percentages of economically disadvantaged students tend to have somewhat lower attendance rates. While not as strong as the other correlations, it still indicates a fair relationship between economic factors and school attendance. Correlation between Dropout Rate and College Readiness: -0.301 This weak to moderate negative correlation indicates that higher dropout rates are associated with lower college readiness scores. While the relationship exists, it’s not as strong as some of the other correlations.