Research Data Selection

library(readxl)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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

setwd("~/PAD 6833/Research Data Selection")
Border_kids<-read_excel("Border_kids.xlsx")

# 1) summary(data$x)
summary(Border_kids$`Children in CBP custody`)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##     7.0    26.0    54.0   148.9   261.0   531.0     701

#2) hist(data$x) - for continuous variables
hist(Border_kids$`Children in CBP custody`)

#3) plot(data$x,data$y) - to compare variables
plot(Border_kids$`Children in CBP custody`, Border_kids$`Children in HHS Care`)

#4) cor(data$x,data$y) - to see a correlation between two variables
 
Border_kids<-Border_kids %>% drop_na()
cor(Border_kids$`Children in CBP custody`,Border_kids$`Children in HHS Care`)

## [1] 0.9312843

#This is a strong positive correlation