Stress testing involves evaluating the impact of extreme, but plausible, scenarios that are not considered by value at risk (VaR) or expected shortfall (ES) models. If there is one lesson to be learned from the market turmoil that started in the summer of 2007, it is that more emphasis should be placed on stress testing and less emphasis should be placed on the mechanistic application of VaR/ES models. VaR/ES models are useful, but they are inevitably backward looking. Risk management is concerned with what might happen in the future.
This chapter considers the different approaches that can be used to generate scenarios for stress testing and how the results should be used. It explains that the financial crisis of 2007 and 2008 has caused regulators to require banks to conduct more stress testing and that increasingly regulators are defining the stress tests themselves in an attempt to ensure that banks have sufficient capital to withstand adverse scenarios.
The most popular approach for calculating market risk VaR or ES is the historical simulation approach covered in Chapter 13. This approach assumes that data from the last few years is a good guide to what will happen over the next 1 to 10 days. But if an event has not occurred during the period covered by the data, it will not affect the results when the basic methodology in Section 13.1 is used.
We have discussed a number of ways VaR/ES calculations ...