In United States ex rel. Martin et al. v. Life Care Centers of American, Inc., the Court held that the government could extrapolate from a random sample in order to impose False Claims Act (FCA) liability against Life Care Centers of American Inc. (Life Care) for a substantially larger universe of claims.

In order to prove FCA liability, the government sought to use a random sample of 400 admissions from 82 Life Care facilities spread over approximately 6 year period and then extrapolate the resulting error rate to a sample universe of more than 50,000 patient admissions, comprising more than 150,000 claims. Life Care moved for partial summary judgment on the basis that the government could not satisfy its burden of proof based on statistical sampling and extrapolation.

The Court rejected Life Care’s arguments and denied its motion for summary judgment. The Court held that the general purpose of statistical sampling is to “provide a means of determining the likelihood that a large sample shares characteristics of a smaller sample”, noting that statistical sampling has “become commonplace in certain types of litigation,” and is generally accepted by courts. In the FCA context, the court held that “in view of the enormous logistical problems of [enforcement of government programs], statistical sampling is the only feasible method available.”