In US v. Ahanmisi, a case involving the preparation of false tax returns, the Fourth Circuit held that the government did not meet its burden of establishing a reasonable aggregate of the total tax loss.  Rather than using a random selection of tax returns to determine the tax loss estimate, the government used a non-random sample of returns.  Such an approach, according to the Fourth Circuit, may have potentially skewed the average tax loss figure, failing to provide a reasonable estimate based on the available facts.