Modeling Stock Market Volatility in India: A Comparison of Univariate Deterministic Models
ICFAI Journal of Applied Finance, pp. 19-33, October 2003
19 Pages Posted: 23 Sep 2004
Abstract
There are various conflicting evidences in existing literature about the predicting power of different volatility-forecasting models. There are evidences in favor of the simpler regression model (Dimson and Marsh 1990), as well as complex GARCH family models (Akgiray 1989, Pagan and Schwert 1989, and Brailsford and Faff 1996). In this paper, monthly volatility of market indices (Sensex & S&PCNX-Nifty) of Indian capital markets has been modeled using eight different univariate models. Out-of-sample forecasting performance of these models has been evaluated using different symmetric, as well as asymmetric loss functions. The GARCH (1,1) model has been found to be the over all superior model based on most of the symmetric loss functions though ARCH (9) has been found to be better than the other models for investors who are more concerned about under predictions than over predictions.
Keywords: Forecasting, volatility, GARCH
JEL Classification: C52, C53, C59
Suggested Citation: Suggested Citation