基于ARIMA与GARCH模型的国际油价预测比较分析

在分析影响油价波动因素的基础上,利用1986年1月至2010年12月的WTI国际原油价格月度数据,分别建立ARIMA和GARCH模型对油价进行预测。并通过对2011年1月至2012年4月WTI原油价格进行外推预测,检验模型的预测效果。比较分析发现,在短期预测中,ARIMA和GARCH模型对油价的预测均比较准确,但当油价由于受到重大事件的影响而有较大波动时,模型的预测精度下降;在长期预测中,GARCH模型的预测效果优于ARIMA模型;整体来看,GARCH模型预测的精度高于ARIMA模型。因此,在国际油价预测中,用GARCH模型是比较合适的。

Comparative analysis of the international oil price forecast based on the ARIMA and GARCH models

Based on the analysis of impact factors on oil price fluctuations,from January 1986 to December 2010,WTI crude oil price of monthly data,creation of ARIMA and GARCH models for forecasting oil prices.And by extrapolation from January 2011 to April 2012 WTI crude oil price forecast,forecast effect of testing models.Comparative analysis found that in short-term prediction,ARIMA and GARCH model on oil price forecasts are more accurate,but when oil prices due to the major events and large fluctuations,model prediction accuracy of decline in long-term projections,forecasting of GARCH model better than ARIMA models;overall,GARCH models forecasting accuracy than the ARIMA model.Therefore,in the international oil price forecasting,GARCH models are appropriate.