Combining Stock Market Volatility Forecasts Using a Bayesian Technique

Forecasting stock market volatility is an important and challenging task for both academic researchers and business practitioners. The recent trend to improve the prediction accuracy is to combine individual forecasts using a simple average or weighted average where the weight reflects the inverse of the prediction error. In the existing combining methods, however, the errors between actual and predicted values are equally reflected in the weights regardless of the time order in a forecasting horizon. In this paper, we present a new approach where the forecasting results of the Generalized Autoregressive Conditional Heteroskedastic (GARCH), the Exponential GARCH (EGARCH), and random walk models are combined based on the weights that can be interpreted as Bayesian posterior probabilities of the various prediction models and are computed online. The results of an empirical study indicate that the proposed method has a better accuracy than the GARCH, EGARCH and random walk models, and also combining methods based on using the Mean Absolute Percentage Error(MAPE) for the weight.