Estimation of Expected Shortfall Based on Conditional Extreme Value Theory Using Multifractal Model and Intraday Data in Tehran Stock Exchange

After the financial crisis in 2008, market practitioners and financial researchers began to attach more importance to risk measurement and modeling. Expected shortfall is recognized risk measures in financial literature.

By the estimation of expected shortfall as a coherent risk measure, and by use of conditional extreme value theory and combining new volatility measures, this research attempts to introduce a new model for risk measurement. Intraday data has been used in this research in order to estimate mentioned risk measures.

The results show that in comparison with alternative models, such as GARCH conditional peak over threshold models, multifractal conditional peak over threshold models, which utilize intraday data, perform better in risk estimation. In addition, the use of extreme value theory brings about more favorable results in risk estimation. In this research, we use a new back-testing models in order to back-test expected shortfall.

The use of the normal distribution function for the disruption components to estimate the expected drop has not been successful, and has led to an estimate of the low risk category. The use of Student's t-distribution in estimating risk measures has been acceptable, although in some cases it has led to an estimate of high risk. Considering extreme value theory of value in the above models has in most cases led to improved model performance. This means that it has moderately adjusted the estimates of the upper hand and the estimates of the.