Mortgage Lending Discrimination and Racial Differences in Loan Default
Posted: 1 Mar 1996
There are 2 versions of this paper
Mortgage Lending Discrimination and Racial Differences in Loan Default
Mortgage Lending Discrimination and Racial Differences in Loan Default
Date Written: Undated
Abstract
This paper performs a theoretical analysis of the use of racial differences in loan default to test for mortgage lending discrimination. The default approach has received considerable attention in the press and in academic arenas, and yet the theory underlying this approach has not been carefully explored. The loan process is thought to create a selected sample of loans. If mortgage lenders discriminate by holding minorities to a higher standard, the sample selection bias in the minority sample of loans will be more extreme than the bias in the majority sample, and the sample of minority loans should exhibit lower default rates than the majority sample. This paper examines the default approach explicitly in this sample selection framework and observes that the approach suffers from heteroscedasticity bias because loan defaults are a discrete dependent variable. In addition, the paper examines the impact of correlations between race and the unobservables in the loan approval and default equations. Both of these correlations are shown to bias the default approach away from finding discrimination under the standard assumptions.
JEL Classification: J71, J15
Suggested Citation: Suggested Citation