Heterogeneous Volatility Information Content for the Realized GARCH Modeling and Forecasting Volatility

Xu Wen (), Aschakulporn Pakorn () and Zhang Jin E. ()
Additional contact information
Xu Wen: Department of Accountancy and Finance, 202495 Otago Business School, University of Otago , Dunedin, New Zealand
Aschakulporn Pakorn: Department of Accountancy and Finance, 202495 Otago Business School, University of Otago , Dunedin, New Zealand
Zhang Jin E.: Department of Accountancy and Finance, 202495 Otago Business School, University of Otago , Dunedin, New Zealand

Studies in Nonlinear Dynamics & Econometrics, 2025, vol. 29, issue 6, 769-785

Abstract: As the demand for accuracy in volatility modeling and forecasting increases, the literature tends to incorporate different volatility measures with heterogeneous information content to construct the hybrid volatility model. This study focuses on one of the popular hybrid volatility models: the Realized Generalized Autoregressive Heteroskedasticity (Realized GARCH) and embeds various volatility measures, including the CBOE VIX, VIX1D, Realized Volatility, and Daily Range to examine their heterogeneous impact on the conditional volatility estimation and forecasting. To evaluate the impact of the volatility measures, we first construct a volatility response function. This involves calculating the difference in one-step-ahead conditional volatility forecasts that incorporate information from both return and volatility measures against the forecasts based on return innovations only. Subsequently, the variance share is calculated to evaluate its role in explaining future variations in the Realized GARCH. Our results show that among these four volatility measures, VIX is the most informative volatility. Although VIX1D is overemphasized by the literature, its significance in volatility forecasting remains substantial, confirming that risk-neutral volatility measures are generally more informative than physical measures. Finally, we also find that incorporating multiple risk-neutral volatility measures does not improve forecasting performance compared to using a single measure due to overlapping information.

Keywords: Realized GARCH model; variance share; volatility modeling and forecasting; model confidence set (search for similar items in EconPapers)
JEL-codes: C10 C52 G17 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/snde-2024-0013 (text/html)
For access to full text, subscription to the journal or payment for the individual article is required.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bpj:sndecm:v:29:y:2025:i:6:p:769-785:n:1006

Ordering information: This journal article can be ordered from
https://www.degruyte ... ournal/key/snde/html

DOI: 10.1515/snde-2024-0013

Access Statistics for this article

Studies in Nonlinear Dynamics & Econometrics is currently edited by Bruce Mizrach

More articles in Studies in Nonlinear Dynamics & Econometrics from De Gruyter
Bibliographic data for series maintained by Peter Golla ().