DocumentCode :
2654073
Title :
Application of an EWMA Combining Technique to the Prediction of Stock Market Volatility
Author :
Jing-rong, DONG
Author_Institution :
Chongqing Normal Univ., Chongqing
fYear :
2007
fDate :
20-22 Aug. 2007
Firstpage :
1844
Lastpage :
1848
Abstract :
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 Generalized Autoregressive Conditional Heteroskedastic (GARCH), stochastic volatility (SV), and random walk models are combined based on a weight that reflects the inverse of the exponentially weighted moving average (EWMA) of the Mean Absolute Percentage Error (MAPE) of each individual prediction model. The results of an empirical study indicate that the proposed method has a better accuracy than the GARCH, SV, and random walk models, and also combining methods based on using the MAPE for the weight.
Keywords :
autoregressive processes; random processes; risk analysis; stock markets; exponentially weighted moving average; generalized autoregressive conditional heteroskedastic; mean absolute percentage error; prediction error; random walk model; simple average; stochastic volatility; stock market volatility forecasting; stock market volatility prediction; weighted average; Accuracy; Computer crashes; Conference management; Econometrics; Economic forecasting; Engineering management; Predictive models; Regulators; Stochastic processes; Stock markets; EWMA; GARCH; SV; combining forecasts; random walk; stock market volatility;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Management Science and Engineering, 2007. ICMSE 2007. International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-7-88358-080-5
Electronic_ISBN :
978-7-88358-080-5
Type :
conf
DOI :
10.1109/ICMSE.2007.4422108
Filename :
4422108
Link To Document :
بازگشت