
“Robust Stress Testing” by Rhys Bidder
Economics Seminar
Authors:
Rhys Bidder
Federal Reserve Bank of San FranciscoAndrew McKenna
Federal Reserve Bank of San Francisco
In recent years, stress testing has become an important component of financial and macroprudential regulation. Despite the general consensus that such testing has been useful along certain dimensions, the techniques of stress testing are still being honed. This partly reflects certain concerns that have been raised over the nature of the stress test scenarios as currently applied. In response to these concerns we propose to use the methods of Robust Control analysis to identify and construct adverse scenarios that are naturally interpretable as stress tests. These scenarios emerge from a particular pessimistic twist to a benchmark forecasting model that posits (1) a law of motion for a state and (2) the dependence of bank `performance' on this state. This pessimistic twist is often referred to as a `worst case distribution'. We will use this distribution to generate candidate scenarios and simulations for stress tests.