Focusing on older adults (65+), highlighting preventive care dispairites in Texas counties. Key variables: “Vacc” (% Medicare enrollees with annual flu shot), “Hosp” (hospital stays per 100k Medicare enrollees), and Mammo”(% female Medicare enrollees 65-74 with annual mammogram screening).

older_data <- raw_data[, c(3, 74, 99, 106)] 

colnames(older_data) <- c("County", "Vacc", "Hosp", "Mammo") 

older_data[,2:4] <- lapply(older_data[,2:4], as.numeric) 

older_data <- na.omit(older_data) 
# Remove NAs + bad values properly 

older_data$Vacc <- as.numeric(as.character(older_data$Vacc)) 

older_data$Hosp <- as.numeric(as.character(older_data$Hosp)) 

older_data$Mammo <- as.numeric(as.character(older_data$Mammo)) 

# Drop rows with any NA 

older_data <- older_data[complete.cases(older_data[,2:4]), ] 

nrow(older_data)  # ~200 good rows now 
## [1] 239
head(older_data) 
## # A tibble: 6 × 4
##   County     Vacc  Hosp Mammo
##   <chr>     <dbl> <dbl> <dbl>
## 1 Anderson   25    3528    38
## 2 Andrews    28    3684    37
## 3 Angelina   26.7  3332    40
## 4 Aransas    26    1640    45
## 5 Archer     19.7  2705    40
## 6 Armstrong  18.5  1964    36

SUMMARY

summary(older_data$Vacc) 
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   13.60   22.80   25.20   25.87   28.25   44.20
summary(older_data$Hosp) 
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##     906    2432    3023    3036    3674    6214
summary(older_data$Mammo) 
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   14.00   30.00   36.00   34.67   40.00   55.00

HISTOGRAMS

hist(older_data$Vacc) 

hist(older_data$Hosp) 

hist(older_data$Mammo)

PLOTS

plot(older_data$Vacc, older_data$Hosp) 

plot(older_data$Mammo, older_data$Hosp) 

plot(older_data$Vacc, older_data$Mammo)

CORRELATIONS

cor(older_data$Vacc, older_data$Hosp) 
## [1] 0.1196028
cor(older_data$Mammo, older_data$Hosp) 
## [1] -0.1335233
cor(older_data$Vacc, older_data$Mammo) 
## [1] -0.5878529