Modeling and forecasting the volatility of Tehran Exchange Dividend Price Index (TEDPIX)
The present research, analyses the forecasting performance of a variety of conditional and non-conditional models of TEDPIX volatility at the daily frequencies performance criterion namely the root mean square error (RMSE).
Under RMSE, results show MA250 and CGARCH models had better performance between non conditional and conditional models respectively. Results of combined models also show that non-conditional models have had better performance relative to conditional models. Further, result of Diebold- Mariano test shows that the forecasting performance of MA 250 is not statistically significant from that of CGARCH.