I have a dataset containing 2m observations of loan data from a specific lending platform, with info regarding the loan itself and the borrower, and this data covers over 900 USA zip codes and spans over 6 years from 2013-2019. So for each zip code in each year, I have a few hundred observations roughly on average. I want to see how this lending platform's ability to lend is affected by different variables, like the credit card market loan market concentration ratio or bank branches per capita in that zip code, potentially using the number of loans the platform originated in that zip code in that year as the dependent variable. What would be the best regression type to use in this instance?
-
Login or Register
- Log in with
Comment