Forecasting Value-at-Risk Using Conditional Volatility Models: Evidence from Tehran Stock Exchange

Abstract

In this paper, we investigate the performance of parametric ARCH class models to forecast out-of-sample VaR for two portfolios of Tehran Stock Exchange (TSE) companies (Market portfolio and a portfolio of 50 liquid companies), using a number of distributional assumptions and sample sizes at low and high confidence levels. We find, first, that leptokurtic distributions are able to produce better oneday- ahead and 10-day-ahead VaR forecasts; second, the choice of sample size is important for the accuracy of the forecasts.

Keywords

• backtesting
• c52
• conditional volatility
• jel classification: c22
• loss function
• value at risk (var)
• c53
• g15
• g15.