Forecasting realized volatility of crude oil futures with equity market uncertainty

ABSTRACT

This paper examines whether the equity market uncertainty (EMU) index contains incremental information for forecasting the realized volatility of crude oil futures. We use 5-min high-frequency transaction data for WTI crude oil futures and develop six heterogeneous autoregressive (HAR) models based on classical HAR-type models. The empirical results suggest that EMU contains more incremental information than the economic policy uncertainty (EPU) for forecasting the realized volatility of crude oil futures. More importantly, we argue that EMU is a non negligible additional predictive variable that can significantly improve the 1-day ahead predictive accuracy of all six HAR-type models, and improve the 1-week ahead forecasting performance of the HAR-RV, HAR-RV-J, HAR-RSV, HAR-RV-SJ models. These findings highlight a strong short-term and a weak mid-term predictive ability of EMU in the crude oil futures market.

KEYWORDS:

• Realized volatility
• volatility forecasting
• equity market uncertainty
• HAR-RV model
• crude oil futures

JEL CLASSIFICATION:

• B41
• C22
• C53

Acknowledgments

The authors would like to show their sincere gratitude to the support given by the National Natural Science Foundation of China (Nos. 71873146, 71873147, 71431008).

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

¹ In order to test the robustness of the results for out-of-sample evaluation, we compare the MCS test results for all the volatility models in one model set. The results are consistent with the results in Section 6.2. The results are not reported to save space but are available upon request. We sincerely appreciate one anonymous referee for noting this issue.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China: [Grant Numbers 71873146, 71873147, 71431008].