Forecasting stock market volatility using implied volatility: evidence from extended realized EGARCH-MIDAS model

ABSTRACT

This paper extends the realized EGARCH-MIDAS (REGARCH-MIDAS) model to incorporate implied volatility (IV) derived from option prices. The extension allows us to examine the incremental information content of IV for forecasting volatility. An empirical investigation with S&P 500 index shows that IV contains valuable information for forecasting volatility. Our proposed model provides more accurate out-of-sample volatility forecasts compared to the EGARCH, the REGARCH and the REGARCH-MIDAS models as well as the EGARCH-IV and the REGARCH-IV models.

KEYWORDS:

• Realized EGARCH-MIDAS Realized kernel Implied volatility Forward-looking information Volatility forecasting

JEL CLASSIFICATION:

• C32
• C51
• C53

Acknowledgments

We would like to thank the Editor and an anonymous referee for the insightful comments and suggestions that greatly improved the paper.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

¹ Following Hansen and Huang (2016), we assume that $\mu =0$ and $\varphi =1$ to facilitate model estimation.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [71501001,71971001];Foreign Visiting Scholar Program for Excellent Youth Scholars in Universities of Anhui Province [gxfx2017031];Southern Jiangsu Capital Markets Research Center [2017ZSJD020];University Natural Science Research Project of Anhui Province [KJ2019A0659].