A semiparametric approach to short-term oil price forecasting

In this paper it is shown how the GARCH properties of oil price changes can be employed to forecast the oil price distribution over short-term horizon s. The forecasting methodology is semiparametric and it is based on the boo tstrap approach. The results of an out-of-sample forecasting exercise, carr ied out using the Brent oil price series, suggest that the forecasting appr oach can be used to obtain a performance measure for the forward price, in addition to compute interval forecasts for the oil price. (C) 2001 Elsevier Science B.V. All rights reserved.