Composite quantile regression for GARCH models using high-frequency data

Meng Wang, Zhao Chen, Christina Dan Wang

Research output: Contribution to journalArticle

Abstract

The composite quantile regression (CQR) method is newly proposed to estimate the generalized autoregressive conditional heteroskedasticity (GARCH) models, with the help of high-frequency data. High-frequency intraday log-return processes are embedded into the daily GARCH models to generate the corresponding volatility proxies. Based on proxies, the parameter estimation of GARCH model is derived through the composite quantile regression. The consistency and the asymptotic normality of the proposed estimator are obtained under mild conditions on the innovation processes. To examine the finite sample performance of our newly proposed method, simulation studies are conducted with comparison to several existing estimators of the GARCH model. From the simulation studies, it can be concluded that the proposed CQR estimator is robust and more efficient. An empirical analysis on high-frequency data is presented to illustrate the new methodology.

Original languageEnglish (US)
Pages (from-to)115-133
Number of pages19
JournalEconometrics and Statistics
Volume7
DOIs
StatePublished - Jul 1 2018

Fingerprint

Conditional Heteroskedasticity
High-frequency Data
Quantile Regression
Composite
Simulation Study
Estimator
Regression Estimator
Empirical Analysis
Asymptotic Normality
Model
Volatility
Parameter Estimation
Autoregressive conditional heteroskedasticity
Quantile regression
High-frequency data
Methodology
Estimate
Simulation study

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

Wang, Meng ; Chen, Zhao ; Wang, Christina Dan. / Composite quantile regression for GARCH models using high-frequency data. In: Econometrics and Statistics. 2018 ; Vol. 7. pp. 115-133.
@article{9a26ef2494d243488321c5f4c3dd1b54,
title = "Composite quantile regression for GARCH models using high-frequency data",
abstract = "The composite quantile regression (CQR) method is newly proposed to estimate the generalized autoregressive conditional heteroskedasticity (GARCH) models, with the help of high-frequency data. High-frequency intraday log-return processes are embedded into the daily GARCH models to generate the corresponding volatility proxies. Based on proxies, the parameter estimation of GARCH model is derived through the composite quantile regression. The consistency and the asymptotic normality of the proposed estimator are obtained under mild conditions on the innovation processes. To examine the finite sample performance of our newly proposed method, simulation studies are conducted with comparison to several existing estimators of the GARCH model. From the simulation studies, it can be concluded that the proposed CQR estimator is robust and more efficient. An empirical analysis on high-frequency data is presented to illustrate the new methodology.",
author = "Meng Wang and Zhao Chen and Wang, {Christina Dan}",
year = "2018",
month = "7",
day = "1",
doi = "10.1016/j.ecosta.2016.11.004",
language = "English (US)",
volume = "7",
pages = "115--133",
journal = "Econometrics and Statistics",
issn = "2452-3062",
publisher = "Elsevier BV",

}

Composite quantile regression for GARCH models using high-frequency data. / Wang, Meng; Chen, Zhao; Wang, Christina Dan.

In: Econometrics and Statistics, Vol. 7, 01.07.2018, p. 115-133.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Composite quantile regression for GARCH models using high-frequency data

AU - Wang, Meng

AU - Chen, Zhao

AU - Wang, Christina Dan

PY - 2018/7/1

Y1 - 2018/7/1

N2 - The composite quantile regression (CQR) method is newly proposed to estimate the generalized autoregressive conditional heteroskedasticity (GARCH) models, with the help of high-frequency data. High-frequency intraday log-return processes are embedded into the daily GARCH models to generate the corresponding volatility proxies. Based on proxies, the parameter estimation of GARCH model is derived through the composite quantile regression. The consistency and the asymptotic normality of the proposed estimator are obtained under mild conditions on the innovation processes. To examine the finite sample performance of our newly proposed method, simulation studies are conducted with comparison to several existing estimators of the GARCH model. From the simulation studies, it can be concluded that the proposed CQR estimator is robust and more efficient. An empirical analysis on high-frequency data is presented to illustrate the new methodology.

AB - The composite quantile regression (CQR) method is newly proposed to estimate the generalized autoregressive conditional heteroskedasticity (GARCH) models, with the help of high-frequency data. High-frequency intraday log-return processes are embedded into the daily GARCH models to generate the corresponding volatility proxies. Based on proxies, the parameter estimation of GARCH model is derived through the composite quantile regression. The consistency and the asymptotic normality of the proposed estimator are obtained under mild conditions on the innovation processes. To examine the finite sample performance of our newly proposed method, simulation studies are conducted with comparison to several existing estimators of the GARCH model. From the simulation studies, it can be concluded that the proposed CQR estimator is robust and more efficient. An empirical analysis on high-frequency data is presented to illustrate the new methodology.

UR - http://www.scopus.com/inward/record.url?scp=85049523485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049523485&partnerID=8YFLogxK

U2 - 10.1016/j.ecosta.2016.11.004

DO - 10.1016/j.ecosta.2016.11.004

M3 - Article

VL - 7

SP - 115

EP - 133

JO - Econometrics and Statistics

JF - Econometrics and Statistics

SN - 2452-3062

ER -