Ed Gap Data Exploration

Load data

df <- read.csv("ed_gap_and_nces_data_merged.csv")
nrow(df)

## [1] 8903

MI <- subset(df, state_abbrev == "MI")
nrow(MI)

## [1] 568

mean(MI$teacher_to_student_ratio)

## Warning in mean.default(MI$teacher_to_student_ratio): argument is not numeric
## or logical: returning NA

## [1] NA

sum(MI$teacher_to_student_ratio > 18.1)

## [1] 344