My goal for this project was to investigate student loan default rate for post-secondary institutions in the United States. The student loan default rate, also known as cohort default rate, represents the percentage of students at a given college who default on their federal student loans within three years. High student loan default rate can lead to potential issues down the road for students, colleges, and taxpayers alike. In particular, when a college has more than 25% for its student loan default rate, it faces federal sanctions that could make them ineligible from participating in the federal student loan program.
What I did:
- Estimated the cumulative distribution of cohort default rate by institution types
- Determined the probability of institutions having cohort default rate greater than 30% given institution type
- Estimated the cumulative distribution of cohort default rate for all institutions, compared the distribution to Gaussian, and used two different types of 95% confidence intervals to estimate the mean cohort default rate
- Used multiple testing (Wald test and Bonferroni Method) to determine whether there are significant differences in the average cohort default rate between different types of institutions
- Explored factors associated with cohort default rate and built a model for cohort default rate as a function of selected variables