| Abstract [eng] |
In this thesis we take a look at the most desirable properties of risk measures, most commonly used risk measures – Value-at-risk and Expected Shortfall as well as their estimators. Based on these properties we highlight advantages and disadvantages of these risk measures. We focus on robustness of risk measure estimators. By comparing sensitivity functions of different estimators we see that robustness does not only depend on the risk measure, but also on the selected estimator. Afterwards we perform backtesting which allows us to see if less sensitive risk estimators lead to more accurate risk assessment as well as to identify that the Student’s estimator fits our data the best. |
