Introduction to Stress Testing

In the modern risk management practices, the statistical tools and models play a significant role in measuring risk. These statistical models are used to estimate the distribution of future possible outcome, such as that of interest rates, stock prices, etc. One of the most popular measures of risk is Value-at-risk. VaR is defined as the predicted worst-case loss with a specific confidence level (for example, 95%) over a period of time. One shortcoming of VaR is that it does not capture all the possible outcomes. For example, it does not capture sudden, dramatic changes in the financial markets, such as some of the recent financial crisis that we have seen.

In order to overcome this shortcoming, risk managers use the tool called “Stress Testing”.

A very basic definition of stress testing:

Stress testing is a form of testing that is used to determine the stability of a given system or entity. It involves testing beyond normal operational capacity, often to a breaking point, in order to observe the results.

In terms of financial risk management, it involves stressing the portfolio with extreme conditions to see how it will perform. A stress test is a scenario that measures risk under unlikely but plausible events in abnormal markets. For example, what will happen if the interest rates become extremely high, or if there is an unexpected change foreign exchange. The stress testing can be done using many such plausible events or changes in financial variables. While such events of extreme changes will not affect the VaR, the stress testing using such events will tell us more about the expected losses in the given time horizon.

Most banks and financial institutions use stress tests as a complement to value-at-risk. Stress test are more common for portfolios that require managing market risk. The portfolios most suitable for stress testing are the ones that include interest rates, equity, foreign exchange, and commodity-related instruments.

There are two types of stress tests: sensitivity tests, and scenario tests.

Sensitivity analysis identifies how portfolios respond to shifts in relevant economic variables or risk parameters. Scenarios assess the resilience of financial institutions and the financial system to severe but plausible scenarios.

The following is an excerpt from the JP Morgan Chase 2010 annual report describing how they use stress tests:

This content is for paid members only.

Join our membership for lifelong unlimited access to all our data science learning content and resources.