Chen Zhonglu, Ye Yong, Li Xiafei
School of Economics and Management, Southwest Jiaotong University, Chengdu, China.
Resour Policy. 2022 Mar;75:102453. doi: 10.1016/j.resourpol.2021.102453. Epub 2021 Nov 13.
In this study, we focus on the role of jumps and leverage in predicting the realized volatility (RV) of China's crude oil futures. We employ a standard mixed data sampling (MIDAS) modeling framework. First, the in-sample results indicate that the jump and leverage effects are useful in predicting the RV of Chinese crude oil futures. Second, the out-of-sample results suggest that jump has very significant predictive power at the one-day-ahead horizon while the leverage effect contains more useful information for long-term predictions. Moreover, our results are supported by a number of robustness checks. Finally, we find new evidence that the prediction model that considers the leverage effect has the best predictive power during the COVID-19 pandemic.
在本研究中，我们聚焦于跳跃和杠杆效应在预测中国原油期货的已实现波动率（RV）方面的作用。我们采用了标准的混合数据抽样（MIDAS）建模框架。首先，样本内结果表明跳跃和杠杆效应在预测中国原油期货的RV方面是有用的。其次，样本外结果表明，跳跃效应在提前一天的预测中具有非常显著的预测能力，而杠杆效应在长期预测中包含更多有用信息。此外，我们的结果得到了多项稳健性检验的支持。最后，我们发现了新的证据，即在新冠疫情期间，考虑杠杆效应的预测模型具有最佳的预测能力。
