No abstract

We measure the performance of multi‐model inference (MMI) forecasts compared to predictions made from a single model for crude oil prices. We forecast the West Texas Intermediate (WTI) crude oil spot prices using total OECD petroleum inventory levels, surplus production capacity, the Chicago Board Options Exchange Volatility Index and an implementation of a subset autoregression with exogenous variables (SARX). Coefficient and standard error estimates obtained from SARX determined by conditioning on a single ‘best model’ ignore model uncertainty and result in underestimated standard errors and overestimated coefficients. We find that the MMI forecast outperforms a single‐model forecast for both in‐ and out‐of‐sample datasets over a variety of statistical performance measures, and further find that weighting models according to the Bayesian information criterion generally yields superior results both in and out of sample when compared to the Akaike information criterion. Copyright © 2016 John Wiley & Sons, Ltd.

It has recently been suggested that financial speculation is now playing an important role in daily price movements of global oil prices. This raises the question: what are important drivers of price changes given this new speculative regime? We identify new factors of the oil market related to speculation by fitting subset vector autoregression models with exogenous variables (SubVARX) and rank them by importance. Further, to account for model uncertainty and to obtain robust parameter estimation in this study, we apply a bootstrap model selection procedure. We find that certain speculative factors explain a large portion of the variation in oil price for the given data set.

No abstract