Long memory and structural breaks in commodity futures markets


  • We are grateful to an anonymous reviewer whose suggestions have helped us to make our results more robust, to sharpen the exposition and substantially to improve the overall quality of the study. An earlier version of this study was presented at the 12th International Conference on Computing in Economics and Finance in Cyprus and the 1st International Workshop on Computational and Financial Econometrics in Switzerland. We are grateful to participants for constructive comments. Dollery gratefully acknowledges the financial support provided by an ESRC studentship.


This study employs daily data for 14 commodities and three financial assets 1990–2009 to explore the impact of the time series properties of the futures-spot basis and the cost of carry on forward market unbiasedness. The main result is that the basis of 16 assets exhibits both long memory and structural breaks. The long memory in the basis is robust even to the use of break-adjusted data. It implies that the cost-of-carry has long memory which the empirical results confirm using the interest cost as a proxy. These new findings suggest that the forecast error has long memory and are inconsistent with unbiasedness. They could be consistent with a weaker version of market efficiency in the presence of a fractionally integrated, time-varying risk premium but they could also be rationalized by priced noise trader risk with limits to arbitrage in less than fully efficient markets. © 2010 Wiley Periodicals, Inc. Jrl Fut Mark