PERFORMING A STRESS ANALYSIS OVER A FIXED-INCOME ASSET
The emphasis of stress testing is to use it as a complementary tool to Value at Risk (VaR) analysis. Some authors consider stress tests as a fourth method of calculating VaR, along with parametric, Monte Carlo and historical simulation approaches.
In this sense, stress testing adopts a completely opposite approach to the historical simulation method. This method, sometimes referred to as scenario analysis, examines the effect of large simulated movements on key financial variables on the portfolio. It consists of subjective scenarios of interest to determine possible changes in the value of the asset or the portfolio.
Why stress testing is necessary?
Stress tests are designed to estimate potential economic losses in abnormal markets. Historical analysis of markets shows that the yields have “fat tails”. This is so because there are extreme market movements (beyond the confidence interval of 99%) more frequently than a normal distribution would suggest. In other words, despite the fact that the discipline of risk analysis has advanced a great deal, stress testing considers events beyond the statistical discipline: natural disasters, wars, coups, significant adjustments in market valuations, etc.
In this way, stress testing explores a range of potential low-probability events where VaR bands are exceeded dramatically. Thus, stress tests combined with VaR analysis will provide a more comprehensive risk analysis tool.