Medicare fraud costs this country billions of dollars a year and contributes to an ever-expanding debt. Conservatives want to cut spending on Medicare significantly, while liberals champion expanding Medicare. Finding common legislative ground between these positions has proven impossible. As a result, courts play an important role in pushing Medicare providers to stop defrauding the government. Unfortunately, up to the present, courts have rejected statistical methods of proof that could significantly reduce the cost of bringing suits against Medicare fraudsters. Judges who have ruled on the issue cite due process concerns with extrapolating that a care provider likely defrauded the government in a large number of cases from a much smaller subset of purportedly fraudulent claims. This Note provides guidance to courts, arguing that sampling is appropriate in cases against a single defendant with a large number of claims at issue where the alleged fraud is systematic and the variability between claims is relatively limited. Specifically, this Note deals with the realities of estimating a model that seeks to organize claims into categories of liability or nonliability.

* J.D. Candidate, Stanford Law School, 2019; Ph.D. Candidate (Economics), University of Illinois at Chicago, 2019. Thanks to David Studdert, Denise DeArmond, and Sophia Cai for their invaluable suggestions and editing help. Thanks as well to the editors of the Stanford Law Review, especially Isabella Sayyah, for their amazing editing and tireless work.