This paper studies four ARCH type models including ARCH, GARCH, EGARCH and TGARCH at Value at Risk (VaR) estimation. The four models were applied to daily Tehran stock market data to assess each model in estimating one day Value at Risk at various confidence intervals. Our findings suggest that for the daily return of Tehran Stock market, which exhibit fat-tailed and leptokurtic features, the VaR estimates generated by the GARCH-T models have good accuracy at high confidence levels.
