دقت پیش بینی آینده قیمت نفت خام

This paper evaluates the predictive accuracy of 1-, 3-, 6-, 9-, and 12-month ahead crude oil futures prices for 1991.01–2001.12. In addition to testing for unbiasedness, a naive forecasting model is constructed to generate comparable forecasts, as benchmarks. Our empirical findings reveal that futures prices and naive forecasts are unbiased at all forecast horizons. However, the 1-, and 12-month ahead futures prices are the only forecasts outperforming the naive, suggesting their potential usefulness in policy making. Continuing political instability of the Middle East and the inability of OPEC to offset market sentiment, among other factors, may in the future adversely affect the predictive accuracy of the 1- and 12-month ahead futures prices. Accordingly, caution must be exercised when utilizing such prices as a forecasting tool.

The role of commodity and financial futures markets in providing an accurate picture of future movements in spot prices has been an area of extensive empirical investigation. This is particularly true for the crude oil futures markets, as crude oil price changes may potentially have significant effects on the economic performance of both oil importing and oil exporting countries. Sharp increases in crude oil prices adversely affect the economic growth and inflation of oil importing economies. On the other hand, crude oil price deteriorations, like the one in 1998, create serious budgetary problems for oil exporting countries. An effective policy response to such changes requires reliable and accurate short-term and long-term crude oil price forecasts. Whether or not crude oil futures prices provide such forecasts is the question investigated in this paper. Recent studies testing market efficiency in this area offer mixed conclusions. For example, while Quan (1992) and Moosa and Al-Loughani (1994) argue against futures market efficiency in crude oil, Gulen (1998) and Peroni and McNown (1998) present evidence in support of it. Studies by Bopp and Sitzer (1987) and Bopp and Lady (1991) are in favor of market efficiency for the short-term or 1-month ahead futures price, but reject the notion of efficiency for longer-term futures prices. Utilizing the test procedures suggested by Fair and Shiller (1990) and Gulen (1998), this study adds to the literature by evaluating the forecasting performance of the 1- 3-, 6-, 9-, and 12-month ahead futures prices of crude oil for 1991.01–2001.12. In addition to testing for unbiasedness, we shall construct a naive forecasting model to generate comparable forecasts, as benchmarks, to investigate the predictive information content of futures prices. Our empirical findings reveal that futures prices and naive forecasts are unbiased at all forecast horizons. Unlike the 1- and 12-month ahead futures prices, which outperform the naive forecasts, the 3-, 6-, and 9-month ahead futures prices fail to outperform the naive forecasts. This study is organized as follows. Section 2 describes the data and presents the test procedures. Section 3 discusses the empirical results. Section 4 concludes this paper.