###########################################################################
# PUBLG100: Introduction to Quantitative Methods
#
# Week 2 Solutions: Descriptive Statistics
#
#

## ----eval = FALSE--------------------------------------------------------
## # Change your working directory
## setwd("N:/PUBLG100")
## 
## # Check your working directory
## getwd()
## 
## # clear the environment
## rm(list = ls())

## ------------------------------------------------------------------------
library(readxl)
student_data <- read_excel("hsb2.xlsx")

## ------------------------------------------------------------------------
student_data$final_score <- apply(student_data[c("read", "write", "math", "science", "socst")], 
                                  1,
                                  mean)

head(student_data)

## ------------------------------------------------------------------------
mean_final <- mean(student_data$final_score)
mean_final

median_final <- median(student_data$final_score)
median_final

## ------------------------------------------------------------------------
mode_final <- sort(table(student_data$final_score), decreasing = TRUE)[1]
mode_final

## ------------------------------------------------------------------------
student_data$school_type <- factor(student_data$schtyp, labels = c("Public", "Private")) 

## ------------------------------------------------------------------------
table(student_data$school_type)

## ------------------------------------------------------------------------
public_school <- subset(student_data, school_type == "Public")
public_var <- var(public_school$final_score)
public_sd <- sd(public_school$final_score)

## ------------------------------------------------------------------------
private_school <- subset(student_data, school_type == "Private")
private_var <- var(private_school$final_score)
private_sd <- sd(private_school$final_score)

## ------------------------------------------------------------------------
top_public_student <- which.max(public_school$final_score)
top_public_student_id <- public_school[top_public_student,]$id

bottom_public_student <- which.min(public_school$final_score)
bottom_public_student_id <- public_school[bottom_public_student,]$id

## ------------------------------------------------------------------------
top_private_student <- which.max(private_school$final_score)
top_private_student_id <- private_school[top_private_student,]$id

bottom_private_student <- which.min(private_school$final_score)
bottom_private_student_id <- private_school[bottom_private_student,]$id

## ------------------------------------------------------------------------
quantile(student_data$final_score, c(0.2, 0.4, 0.6, 0.8))

## ------------------------------------------------------------------------
plot(student_data$school_type, 
     student_data$final_score, 
     main = "Public v. Private Schools", 
     las = 2)