Study on the Spillover Impact and Forecasting of Crude Oil Prices on Industry Index Fluctuations Based on MS-HAR-TVP Modeling
In the face of the uncertainty caused by commodity price fluctuations on the financial market,this paper further explores the volatility spillover effect of the crude oil market on the domestic stock market under high-frequency conditions.Decomposing the high-frequency volatility with HAR model,the trend and jump volatility spillover caused by crude oil prices on China financial market are imported by the TVP-VAR model,and then combined with the Markov Regime-Switching to propose the MS-HAR-TVP model.An empirical study is conducted on the different impact of crude oil on Coal and Sola energy index,and the model results are evaluated by adopting a rolling window period and the MCS test method.The empirical research shows that the high-frequency volatility spillover after decomposition still has obvious volatility clustering and asymmetry.The trend and jump spillover have a higher ability to predict future volatility.The short-term trend of crude oil is opposite to that of the new energy index but the same as that of the coal index.The MCS test verifies that combining crude oil volatility spillover can significantly improve the in-sample and out-of-sample predictive accuracy of domestic energy index during high volatility periods.Both industry indices have higher out-of-sample predictive accuracy in the trend model(MS-HAR-TVP)and the jump model(MS-HAR-TVP-J/TCJ).
万方数据
维普
