The predictive power of oil price shocks on realized volatility of oil: A note

Resour Policy. 2020 Dec:69:101856. doi: 10.1016/j.resourpol.2020.101856. Epub 2020 Sep 23.


This paper examines the predictive power of oil supply, demand and risk shocks over the realized volatility of intraday oil returns. Utilizing the heterogeneous autoregressive realized volatility (HAR-RV) framework, we show that all shock terms on their own, and particularly financial market driven risk shocks, significantly improve the forecasting performance of the benchmark HAR-RV model, both in- and out-of-sample. Incorporating all three shocks simultaneously in the HAR-RV model yields the largest forecasting gains compared to all other variants of the HAR-RV model, consistently at short-, medium-, and long forecasting horizons. The findings highlight the predictive information captured by disentangled oil price shocks in accurately forecasting oil market volatility, offering a valuable opening for investors and corporations to monitor oil market volatility using information on traded assets at high frequency.

Keywords: Forecasting; Oil; Oil price shocks; Realized volatility; Risk shocks.