The goal of this study is to identify applicant characteristics, disparities, and specialty trends among dual degree (MD-PhD, MD-MPH, MD-MBA, and MD-MSc) applicants.
- 01_TexasSTAR_analysis.Rmd - main R markdown file for statistics and data visualization.
- 02_Doximity_ranker.ipynb - Jupyter notebook for collecting residency rank data from Doximity.
- 03_school_matcher.py - python script to match residency programs by specialty listed in Texas STAR to program names listed in Doximity. Based on fuzzy string matching.
- 04_school_matcher.ipynb - Jupyter notebook for concatenating and cleaning all matched names from Doximity and Texas STAR.
- 05_rankdom_forest.ipynb - Jupyter notebook modeling a random forest classifier to determine feature importance for different degree paths.