Relation between College Costs and Expected Earnings

Edward Harvey, Yifan Li, Sandani Kumanayake

2023-12-15

Introduction

Question

Data

Accessed via Kaggle.com. Four files from two sources:

Variables

Weaknesses

Cleaning

  1. Starting with diversity data
    • Selected university name, state, and total enrollment variables
    • Pivoted wider by name and state to get counts for different student demographics
  2. Joined salary potential data with newly pivoted diversity data based on university name and state
  3. Jointed tuition cost data to new data frame
  4. Cleaned second tuition cost data and joined to new data frame
    • Pivoted wider to get cost breakdown by income level
    • Joined with new data frame by name and state
    • Ultimately did not use this data in the analysis
  5. Removed NAs as appropriate for individual plots
  6. Calculated percentages, geographic regions, and other minor variable changes as necessary for individual plots

Plots

Costs

Expected Earnings

Scatter Plots

Shiny applications not supported in static R Markdown documents

Conclusion