Abstract:

In recent months and years both practitioners and regulators have embraced the idea ofsupplementing VaR estimates with “stress-testing”.  Risk managers are beginning to place anemphasis and expend resources on developing more and better stress-tests.  In the present paper,we hold the standard approach to stress-testing up to a critical light.  The current practice is tostress-test outside the basic risk model. Such an approach yields two sets of forecasts -- one fromthe 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 orrelevance of the results of stress-tests.  Moreover,  how to combine the two forecasts into ausable risk metric is not known.  Instead, we suggest folding the stress-tests into the risk model,thereby requiring all scenarios to be assigned probabilities.

Acknowledgements

I gratefully acknowledge helpful input from Jim O’Brien, Matt Pritsker, PatParkinson and Pat White. Any remaining errors and inaccuracies are mine.  The opinionsexpressed do not necessarily represent those of the Federal Reserve Board or its staff.