Confidence interval Calculation & Evaluating Markov regime switching Precision for Value-at-Risk Estimation: A Case Study on Tehran Stock Exchange Index (TEDPIX)

Value at risk is one of the most common risk measures which, considering its dependency on volatility return, uncertainty of volatility prediction models and existing bias in parameter prediction, is subject to bias. Also the broad usage of this measure has caused anxiety for investors about the estimation accuracy. So, according to the importance of this issue, this study compares precision of Markov Regime Switching GARCH and GARCH in VaR estimation of Tehran Stock Exchange index (TEDPIX) with constructing Bootstrap confidence interval and measures the possibility of rotation and movement of both high and low volatile regime on precision of value at risk estimation. The results show that Markov Regime Switching GARCH lead to more conservative value at risk estimation than GARCH model and it is more suitable for risk aversion investors.