A coherent framework for stress testing

Abstract

In recent months and years, practitioners and regulators have embraced the idea of supplementing value-at-risk estimates with "stress testing". Risk managers are beginning to place an emphasis and expend resources on developing more and better stress tests. In the present paper, the standard approach to stress testing is exposed to a critical light. The current practice is to stress-test outside the basic risk model. Such an approach yields two sets of forecasts - one from the stress tests and one from the basic model. The stress scenarios, conducted outside the model, are never explicitly assigned probabilities. As such, there is no guidance as to the importance or relevance of the results of stress tests. Moreover, it is not known how to combine the two forecasts into a usable risk metric. Instead, the author suggests folding the stress tests into the risk model, thereby requiring all scenarios to be assigned probabilities.