Modelling and Forecasting OPEC Crude Oil Prices Using ARIMA-GARCH Hybrid Model

Document Type : Original Article

Authors

1 Department for Statistics College of Business Studies The Public Authority for Applied Education and Training Kuwait City Kuwait

2 Department of Statistics College of Business Studies The Public Authority for Applied Education and Training

3 Department of Statistics College of Business Studies The Public Authority of Applied Education and Training Kuwait City Kuwait

Abstract

This paper dealt with the application of a hybrid model- by combining the Autoregressive Integrated Moving Average (ARIMA) model with the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) by using the ARIMA model residuals as inputs to the GARCH model- on the time series data of the monthly prices of the barrel of crude oil for the Organization of Petroleum Exporting Countries (OPEC) during the period (January 2003 - May 2018). A number of models were proposed and then compared using the evaluation criteria. The ARIMA (2,2,1) -GARCH (1.1) hybrid model was found to be the most appropriate model for analyzing the data under study and more efficient in forecasting compared to the ARIMA model due to owning lower values of forecasting accuracy criteria (MAPE), (MAE) and (RMSE). Therefore, this model was used to predict twelve monthly values, the first six of which were used to compare with actual ones and the rest to predict future values over the next six months.

Keywords

Files

Share

How to cite

Statistics