Volatility forecasting is an important area of research in financial markets and immense effort has been expended in improving volatility models since better forecasts translate themselves into better pricing of options and better risk management. In this direction, the present paper attempts to model and forecast the volatility (conditional variance) of the S&P CNX Nifty index returns of Indian stock market, using daily data for the period from January 1, 1996 to January 29, 2010. The forecasting models that are considered in this study range from the simple GARCH(1, 1) model to relatively complex GARCH models, including the Exponential GARCH(1, 1) and Threshold GARCH(1, 1) models. Based on out-of-sample forecasts and a majority of evaluation measures, the results show that the asymmetric GARCH models do perform better in forecasting conditional variance of the Nifty returns rather than the symmetric GARCH model, confirming the presence of leverage effect. The findings are consistent with those of Banerjee and Sarkar (2006) that relatively asymmetric GARCH models are superior in forecasting the conditional variance of Indian stock market returns rather than the parsimonious symmetric GARCH models.

Financial market volatility is a central issue to the theory and practice of asset pricing, asset allocation, and risk management. Though earlier financial models assumed volatilities to be constant, it is widely recognized among both practitioners and academics that volatility varies over time. This recognition initiated an extensive research into the distributional and dynamic properties of stock market volatility. Stock volatility is simply defined as a conditional variance, or standard deviation of stock returns that is not directly observable. Since the optimal decision of investors relies on variance of returns that can change over time, it is important to model and forecast conditional variance. Besides, the stock market volatility is important for several reasons. Detection of volatility-trends would provide insight for designing investment strategies and for portfolio management. Accurate forecasts of stock market volatility may improve the performance of option pricing models. In order to value an option precisely, it is important to accurately forecast the future standard deviation of returns over the remaining life of the option. This would be useful for holders and writers of options on the underlying assets (Liu and Morley, 2009). Moreover, the stock market volatility forecast is an important input for dynamic portfolio insurance strategies. Gains on straddles or spreads depend on the volatility of the underlying security. The more volatile a security, the larger the gain to the straddle-trader or the spread-trader. The spread-trader and the straddletrader are not concerned about the direction of change; rather they are concerned about the fluctuations in prices. Hence, there is no gainsaying the statement that volatility estimation is an essential part in most finance-related decisions, be it asset allocation, derivative pricing or risk management. However, the question as to what model should be used to calculate volatility, has no unique answer as different volatility models are proposed in the literature and are being used by practitioners, and these varying models lead to different volatility estimates.

Financial Risk Management Journal, Modeling, Forecasting, Time-Varying Conditional, Volatility, Autoregressive Conditional Heteroscedasticity (ARCH), Generalized Autoregressive Conditional Heteroscedasticity (GARCH) Indian Stock Market.