Forecasting the Real Price of Oil in a Changing World: A Forecast Combination Approach

The U.S. Energy Information Administration (EIA) regularly publishes monthly and quarterly forecasts of the price of crude oil for horizons up to 2 years, which are widely used by practitioners. Traditionally, such out-of-sample forecasts have been largely judgmental, making them difficult to replicate and justify. An alternative is the use of real-time econometric oil price forecasting models. We investigate the merits of constructing combinations of six such models. Forecast combinations have received little attention in the oil price forecasting literature to date. We demonstrate that over the last 20 years suitably constructed real-time forecast combinations would have been systematically more accurate than the no-change forecast at horizons up to 6 quarters or 18 months. The MSPE reductions may be as high as 12% and directional accuracy as high as 72%. The gains in accuracy are robust over time. In contrast, the EIA oil price forecasts not only tend to be less accurate than no-change forecasts, but are much less accurate than our preferred forecast combination. Moreover, including EIA forecasts in the forecast combination systematically lowers the accuracy of the combination forecast. We conclude that suitably constructed forecast combinations should replace traditional judgmental forecasts of the price of oil.

[1]  J. Stock,et al.  Combination forecasts of output growth in a seven-country data set , 2004 .

[2]  F. Diebold,et al.  Structural change and the combination of forecasts , 1986 .

[3]  Halbert White,et al.  Tests of Conditional Predictive Ability , 2003 .

[4]  L. Kilian,et al.  In-Sample or Out-of-Sample Tests of Predictability: Which One Should We Use? , 2002, SSRN Electronic Journal.

[5]  P. K. Verleger.  The Margin, Currency, and the Price of Oil , 2011 .

[6]  What’s the Value of an Energy Economist? , 2008 .

[7]  Todd E. Clark,et al.  Tests of equal predictive ability with Real-Time data. Discussion paper , 2007 .

[8]  Lutz Kilian,et al.  What Central Bankers Need to Know About Forecasting Oil Prices , 2012 .

[9]  The Predictive Content of Commodity Futures , 2014 .

[10]  M. Hashem Pesaran,et al.  Testing Dependence Among Serially Correlated Multicategory Variables , 2006, SSRN Electronic Journal.

[11]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[12]  Alessandro Astolfi,et al.  A remark on the stability of interconnected nonlinear systems , 2004, IEEE Transactions on Automatic Control.

[13]  Lutz Kilian,et al.  The Role of Inventories and Speculative Trading in the Global Market for Crude Oil , 2010 .

[14]  J. Speight.  The Crude Oil Market , 2011 .

[15]  L. Kilian.  Not All Oil Price Shocks are Alike: Disentangling Demand and Supply Shocks in the Crude Oil Market , 2006 .

[16]  Dwight R. Sanders,et al.  Evaluating information in multiple horizon forecasts: The DOE's energy price forecasts , 2009 .

[17]  Kenneth S. Rogoff,et al.  Can Exchange Rates Forecast Commodity Prices? , 2008 .

[18]  Lutz Kilian,et al.  Forecasting the Price of Oil , 2010 .

[19]  James D. Hamilton,et al.  Understanding Crude Oil Prices , 2008 .

[20]  Jonathan H. Wright,et al.  The Information Content of Forward and Futures Prices: Market Expectations and the Price of Risk , 2004 .

[21]  Todd E. Clark,et al.  Approximately Normal Tests for Equal Predictive Accuracy in Nested Models , 2005 .

[22]  L. Kilian,et al.  What Do We Learn from the Price of Crude Oil Futures? , 2007 .

[23]  Lutz Kilian,et al.  Real-Time Forecasts of the Real Price of Oil , 2011 .

[24]  L. Kilian,et al.  Are Product Spreads Useful for Forecasting? An Empirical Evaluation of the Verleger Hypothesis , 2013 .

[25]  Maarten Steinbuch,et al.  String-Stable CACC Design and Experimental Validation: A Frequency-Domain Approach , 2010, IEEE Transactions on Vehicular Technology.

[26]  Thomas A. Knetsch,et al.  Forecasting the Price of Crude Oil Via Convenience Yield Predictions , 2007, SSRN Electronic Journal.

[27]  Francis X. Diebold,et al.  Comparing Predictive Accuracy, Twenty Years Later: A Personal Perspective on the Use and Abuse of Diebold–Mariano Tests , 2012 .

[28]  Chang‐Jin Kim,et al.  State-Space Models with Regime-Switching: Classical and Gibbs Sampling Approaches with Applications , 1999 .

[29]  L. Kilian,et al.  Real-Time Analysis of Oil Price Risks Using Forecast Scenarios , 2011 .

[30]  Robert J. Vigfusson,et al.  Evaluating the Forecasting Performance of Commodity Futures Prices , 2010 .