Enhancing the HAR model: PCA and scaled PCA methods on heterogeneous realized volatilities

Huachen Zhang, Huifang Liu, Han Yan and Shenglin Ma

Politická ekonomie, vol. preprint

Abstract: This study extends the heterogeneous autoregressive (HAR) model by employing the principal component analysis (PCA) and scaled PCA (sPCA) methods on lagged heterogeneous realized volatilities to construct the HAR-PCA and HAR-sPCA models using high-frequency data from 20 stock indices. The in-sample fitting and out-of-sample forecasting performances consistently show that the HAR-PCA and HAR-sPCA models have superior performance. The findings suggest that the heterogeneous principal components of lagged volatilities alleviate the subjectivity associated with the selection of the heterogeneous lag terms. This emphasizes the importance of optimizing the long-period lags under the HAR framework to better capture the heterogeneity of investors.

Keywords: Volatility; heterogenous autoregressive model; principal component analysis; scaled principal component analysis; heterogeneous market hypothesis (search for similar items in EconPapers)
References: Add references at CitEc
Citations:

Downloads: (external link)
http://polek.vse.cz/doi/10.18267/j.polek.1526.html (text/html)
free of charge

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:prg:jnlpol:v:preprint:id:1526

Ordering information: This journal article can be ordered from
Redakce Politické ekonomie, Vysoká škola ekonomická, nám. W. Churchilla 4, 130 67 Praha 3
http://polek.vse.cz

DOI: 10.18267/j.polek.1526

Access Statistics for this article

Politická ekonomie is currently edited by Jiřina Bulisová

More articles in Politická ekonomie from Prague University of Economics and Business Contact information at EDIRC.
Bibliographic data for series maintained by Stanislav Vojir ().