Do extreme shocks help forecast oil price volatility? The augmented GARCH-MIDAS approach

Extreme shocks (e.g., wars and financial crises) cause violent fluctuations in crude oil volatility. In this paper, we first propose GARCH models in the framework of MIDAS augmented to include the impacts of extreme shocks on oil price volatility. In-sample results show that extreme shocks can induce the additional volatility of crude oil. Further, the results from out-of-sample clearly indicate that the crude oil volatility is best fitted by the EGARCH-MIDAS-ES model, which incorporates asymmetric effects in the short-term component and the significant effect of extreme shocks in the long-term component. Additionally, robustness tests confirm that the augmented volatility models can produce better prediction results, both statistically and economically, than the conventional GARCH-MIDAS model. Furthermore, we verify that negative extreme shocks can cause larger volatility, whereas positive extreme shocks of the same magnitude have smaller effects. Our contribution offers fresh insights into energy price volatility forecasting by considering extreme shocks.

Automated summary

This paper proposes a weighted autoregressive conditional heteroskedasticity (ARCH) model in the framework of mixed data sampling (MIDAS) augmented to include the impacts of extreme shocks on oil price volatility. The results show that extreme shocks induce additional volatility in crude oil, and the proposed model, EGARCH-MIDAS-ES, fits the crude oil volatility best. Additionally, robustness tests confirm that the augmented volatility models outperform the conventional GARCH-MIDAS model in terms of prediction accuracy and economic performance. Furthermore, the study finds that negative extreme shocks have a larger effect on volatility compared to positive extreme shocks of the same magnitude.