Is economic policy uncertainty important to forecast the realized volatility of crude oil futures?

ABSTRACT

In this research, we first investigate whether economic policy uncertainty (EPU) index can increase the HAR-RV-type models’ forecast accuracy. In addition, we explore how EPU index can be effectively used to gain larger economic values in the oil futures market. To this end, this research provides a new perspective on setting thresholds for EPU and examines whether these thresholds can help improve both the forecast accuracy and economic values. Empirical results suggest that the HAR-RV-type models including EPU can generate more accurate forecasts and economic values. The HAR-RV-type models including above-threshold EPU can further improve the forecast accuracy and yield higher economic values by setting specific thresholds for a range of horizons. The findings highlight the importance of EPU and effective way of using EPU in risk management and portfolio strategies that is crucial for investors and policymakers.

KEYWORDS:

• Volatility forecasting
• realized volatility
• economic policy uncertainty
• crude oil futures
• HAR-RV-type models

JEL CLASSIFICATION:

• C22
• C52
• C53

Acknowledgements

The authors are grateful to the Editor and the two anonymous referees for providing thoughtful comments and suggestions that enhanced the quality of this article. The authors are also grateful to the financial support from the Natural Science Foundation of China through grant numbers 71701170, 71371157 and 71671145, 71771124. Feng Ma is also supported by Program for Fundamental Research Funds for the Central Universities [2682017WCX01], and the Humanities and Social Science Fund of Ministry of Education [17YJC790105].

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

¹ The EPU index can be downloaded from the website http://www.policyuncertainty.com/us_monthly.html. More details about EPU index can be found in Baker, Bloom, and Davis (2015).

² As detailed in Zivot and Wang (2005), for the WTI futures contract, we apply a filter to remove: (a) transactions outside the official trading period, (b) transactions with a variation of more than 5% in absolute value compared to the previous transaction and (c) transactions not reported in chronological order. The same practices are used in Chevallier and Sévi (2012) and Sévi (2014). Pit trading takes place between 9:30 am (ET) and 4:15 pm (ET).

³ We do not report all estimation results in the table, but they are available upon request.

Additional information

Funding

This work was supported by the Natural Science Foundation of China [71701170, 71371157 and 71671145, 71771124]; Program for Fundamental Research Funds for the Central Universities [2682017WCX01]; the Humanities and Social Science Fund of Ministry of Education [17YJC790105].