Publication Type

Journal Article

Version

submittedVersion

Publication Date

7-2023

Abstract

The log realized volatility (RV) is often modeled as an autoregressive fractionally integrated moving average model ARFIMA(1,d,01,d,0). Two conflicting empirical results have been found in the literature. One stream shows that log RV has a long memory (i.e., the fractional parameter d > 0). The other stream suggests that the autoregressive coefficient α is near unity with antipersistent errors (i.e., d α close to 0 and d close to 0.5) from Model 2Model 2 (ARFIMA(1,d,01,d,0) with α close to unity and d close to –0.5). An intuitive explanation is given. For the 10 financial assets considered, despite that no definitive conclusions can be drawn regarding the data-generating process, we find that the frequency domain maximum likelihood (or Whittle) method can generate the most accurate out-of-sample forecasts.

Keywords

long memory, fractional integration, roughness, short-run dynamics, realized volatility

Discipline

Econometrics

Research Areas

Econometrics

Publication

Management Science

Volume

69

Issue

7

First Page

3861

Last Page

3883

ISSN

0025-1909

Identifier

10.1287/mnsc.2022.4552

Publisher

Institute for Operations Research and Management Sciences

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1287/mnsc.2022.4552

Included in

Econometrics Commons

Share

COinS