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)
setwd("C:/Users/andie/Downloads/nursing_homes_including_rehab_services_current_data")
library(readr)
NH_ProviderInfo_Jul2025 <- read_csv("NH_ProviderInfo_Jul2025.csv")
## Rows: 14752 Columns: 100
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (21): CMS Certification Number (CCN), Provider Name, Provider Address, ...
## dbl  (75): Telephone Number, Number of Certified Beds, Average Number of Res...
## date  (4): Date First Approved to Provide Medicare and Medicaid Services, Ra...
## 
## 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.

Exploratory Statistics #1:

summary(NH_ProviderInfo_Jul2025$`Registered Nurse turnover`)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.00   28.60   42.90   43.83   58.30  100.00    2059

Exploratory Statistics #2:

ggplot(NH_ProviderInfo_Jul2025, aes(x=`Number of Substantiated Complaints`))+
         geom_histogram(binwidth=15)

Exploratory Statistics #3:

ggplot(NH_ProviderInfo_Jul2025, aes(x=`Reported Total Nurse Staffing Hours per Resident per Day`,y=`Overall Rating`))+
  geom_point()
## Warning: Removed 538 rows containing missing values or values outside the scale range
## (`geom_point()`).

Exploratory Statistics #4:

cor(NH_ProviderInfo_Jul2025$`Number of Substantiated Complaints`, NH_ProviderInfo_Jul2025$`Overall Rating`, use= "complete.obs")
## [1] -0.4129623