Beginning in 1998, U.S. commercial banks with significant trading activities must hold capital against their defined market risk exposure. Under the current regulatory guidelines, this capital charge is a function of banks' own value-at-risk (VaR) estimates. Two hypothesis-testing methods for evaluating VaR estimates have been proposed; namely, the binomial and the interval forecast methods. As shown in a simulation exercise, the tests generally have low power and thus are prone to misclassifying inaccurate VaR estimates as "acceptably accurate". An alternative evaluation method, based on loss functions that capture specific regulatory concerns, is proposed. Simulation results indicate that this method is capable of distinguishing between VaR estimates generated by accurate and alternative VaR models. The additional information provided by this method, as well as its flexibility with respect to the specification of the loss function, make a reasonable case for its use in the regulatory evaluation of VaR estimates.
