top of page


Correlated Losses in Federal Crop Insurance

Jonathon Siegle, Victor Gardner


The USDA keeps public data on the federal crop insurance program, and serves as a trove of agricultural data, albiet with messy inter-relations and endogeneity problems. Cross-crop correlations in losses are useful to investigate for both portfolio and actuarial purposes. This project explores models to find key explanatory variables, including crop pairs with correlated indemnities.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page