Forecasting Tehran Dividend Stock Price Index volatility: a comparative analysis of Riskmetric and GARCH models

Forecasting of volatility is a critical activity in financial markets. It has a very wide sphere of influence including " investment, security valuation, risk management and monetary policy making". These concerns clearly have particular value in economic decision-making. So, this create the obvious questions: how can we effectively forecast volatility and is it possible to clearly identify a preferred technique? Various methods by which such forecasts can be achieved have been developed in the literature and applied in practice. Such techniques range from the extremely simplistic models that use naïve (random walk) assumptions through to the relatively complex conditional heteroskedastic models of the GARCH family. This paper evaluates the out-of-sample forecasting accuracy of six models for daily volatility of Tehran Dividend Stock Price Index(TEDPIX) during the period from the start of 1378 to the end of 1387(2355 observation). The first 2300 observation is retained for the estimation of parameters and remaining sample is for the forecast period. The following models are employed: Riskmetric model and the GARCH genre of models including GARCH, EGARCH,APARCH,TARCH and IGARCH. These models compare with eachother for selecting the model with best forecasting performance.To this end, we use three error statistics: MAE,RMSE and Theil to evaluate the performance of the competing models. According to all of these statistics; the Riskmetric model provides superior forecasts of volatility. On the other hand, EGARCH model provides worst forecasting performance.