#My dataset is the HUD Consolidated Planning CHAS Data (2107-2021 ACS 5 year estimate; county summary level) This data can be found at this link: https://www.huduser.gov/portal/datasets/cp.html
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 3.5.2 ✔ 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("readxl")
HousingData <- read_csv("Table1.csv")
## Rows: 3221 Columns: 300
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): source, sumlevel, geoid, name, st, cnty
## dbl (294): T1_est1, T1_est2, T1_est3, T1_est4, T1_est5, T1_est6, T1_est7, T1...
##
## 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.
summary(HousingData$T1_est1)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 30 4165 9820 38872 25550 3342810
hist(HousingData$T1_est1)
plot(HousingData$T1_est1,HousingData$T1_est2)
cor(HousingData$T1_est1,HousingData$T1_est2)
## [1] 0.9817561