Long memory investigation and application of wavelet decomposition to improve the performance of stock market volatility forecasting

Subject Areas : Financial Knowledge of Securities Analysis

شمس اله شیرین بخش ¹ (ندارد)
اسماعیل نادری ² (مسئول مکاتبات)
نادیا گندلی علیخانی ³ (ندارد)

Received: 2012-08-05 Accepted : 2012-11-10 Published : 2013-03-10

Keywords: Forecasting, Exchange Market, long memory, wavelet decomposition, ARFIMA, FIGARCH,

Abstract :

Because of very large frequency and volatility in Financial markets Indicators, acertain type of non stationary is created that it refers to the fraction non stationary. Thiscauses, provides Long memory in this type of time series. Hence, this study has inaddition to examine the existence of the long memory in both mean and varianceequations in the return series of Tehran stock exchange, Pays to forecasting the volatilityof this index. For this purpose, the daily data from fifth Farvardin 1388 to eighteenthOrdibehesht 1391 is used. Our results confirm the existence of Long Memory in bothmean and variance equations. However, among others, based on the information criteriaand MSE, ARFIMA (1,2)-FIGARCH(BBM) model has been selected as the bestspecification to model and forecast the volatility of Tehran stock exchange’s return. Aswell, in order to Forecasting the volatility of this series, was used Combination of theabove model with Level and decomposed data. The results show that, according to theforecasting error criteria (MSE and RMSE), the result of model’s based on decomposeddata (with wavelet technique), more acceptable.