An integrated stress testing framework via Markov switching simulation

ABSTRACT Capturing tail events, especially those that include the rare possibility of severe loss, is one of the important objectives of modern risk analysis. However, the past behavior of financial data is not necessarily an accurate predictor of possible scenarios in the future. The economic turmoil of recent years has resulted in calls for a more forward-looking approach to financial risk management that integrates expert knowledge on plausible future scenarios with classical risk management models calibrated on past behavior. As a complementary risk analysis tool, stress testing is receiving more and more attention, both from regulators and from practitioners. Nevertheless, classical risk analysis models, such as value-at-risk models, that are based on historical data, are often disconnected from stress testing. This disconnection can prevent a comprehensive view of the risk profile of a financial institution. This paper proposes a multiperiod switching simulation based method for integrated stress testing risk analysis that incorporates plausible events that are not necessarily captured in historical data or in historical stressed calibration of risk models. Our application focuses on the integration of rare stress events and model stress into a market risk portfolio. However, the proposed method is also applicable to other financial risk models, eg, portfolio credit risk models. An integrated risk model and stress testing framework not only leads to forward-looking tail risk measurement, which mitigates the black swan effect, but also takes stress testing into advanced risk management decision making analysis, such as scenario-based portfolio optimization.