## Consider some national hospital data:
## https://roualdes.us/data/hospital.csv. Hospital, as clean as they
## are, are notorious places to acquire infections. We'll consider
## the variable infection_risk across four different regions of the
## U.S. for randomly selected hospitals.
## Make an apprioriate plot to investigate the mean of infection_risk
## by region.
## State the three assumptions of ANOVA. Comment on the validity of
## each of the assumptions.
## Set up appropriate hypothesis for ANVOA, to test the mean of
## infection_risk by region. Pick a level of significance.
## Evaluate your hypothesis and conclude in context.
## Make another appropriate plot for ANOVA. You're specifically
## looking for a measure of center (mean or median), a measure of
## variation (sd/var or IQR), and a measure of skew. Try ggplot
## Hint: use the cheatsheet in RStudio