On the Robustness of Racial Disrcimination Findings in Motgage Lending Studies

That mortgage lenders have complex underwriting standards, often differing legitimately from one lender to another, implies that any statistical model estimated to approximate these standards, for use in fair lending determinations, must be misspecified. Exploration of the sensitivity of disparate treatment findings from such statistical models is, thus, imperative. We contribute to this goal. This paper examines whether conclusions from several bank-specific studies, undertaken by the Office of the Comptroller of the Currency, are robust to changes in the link function adopted to model the probability of loan approval and to the approach used to approximate the finite sample null distribution for the disparate treatment hypothesis test. We find that discrimination findings are reasonably robust to the range of examined link functions, which supports the current use of the logit link. Based on several features of our results, we advocate regular use of a resampling method to determine p-values.