A residual-based test for autocorrelation in quantile regression models

Lijuan Huo, Tae-Hwan Kim, Yunmi Kim, Dong Jin Lee

Research output: Contribution to journalArticle

Abstract

Quantile regression (QR) models have been increasingly employed in many applied areas in economics. At the early stage, applications in the QR literature have usually used cross-sectional data, but the recent development has seen an increase in the use of QR in both time-series and panel data sets. However, testing for possible autocorrelation, especially in the context of time-series models, has received little attention. As a rule of thumb, one might attempt to apply the usual Breusch–Godfrey LM test to the residuals of a baseline QR. In this paper, we demonstrate analytically and by Monte Carlo simulations that such an application of the LM test can result in potentially large size distortions, especially in either low or high quantiles. We then propose a correct test (named the QF test) for autocorrelation in QR models, which does not suffer from size distortion. Monte Carlo simulations demonstrate that the proposed test performs fairly well in finite samples, across either different quantiles or different underlying error distributions.

Original languageEnglish
Pages (from-to)1305-1322
Number of pages18
JournalJournal of Statistical Computation and Simulation
Volume87
Issue number7
DOIs
Publication statusPublished - 2017 May 3

Fingerprint

Quantile Regression
Autocorrelation
Regression Model
Time series
Size Distortion
Quantile
Monte Carlo Simulation
Panel Data
Time Series Models
Time Series Data
Economics
Demonstrate
Testing
Baseline
Regression model
Residual-based tests
Quantile regression
Monte Carlo simulation

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

@article{f0080cddc47646f6a919a6dd00dd669f,
title = "A residual-based test for autocorrelation in quantile regression models",
abstract = "Quantile regression (QR) models have been increasingly employed in many applied areas in economics. At the early stage, applications in the QR literature have usually used cross-sectional data, but the recent development has seen an increase in the use of QR in both time-series and panel data sets. However, testing for possible autocorrelation, especially in the context of time-series models, has received little attention. As a rule of thumb, one might attempt to apply the usual Breusch–Godfrey LM test to the residuals of a baseline QR. In this paper, we demonstrate analytically and by Monte Carlo simulations that such an application of the LM test can result in potentially large size distortions, especially in either low or high quantiles. We then propose a correct test (named the QF test) for autocorrelation in QR models, which does not suffer from size distortion. Monte Carlo simulations demonstrate that the proposed test performs fairly well in finite samples, across either different quantiles or different underlying error distributions.",
author = "Lijuan Huo and Tae-Hwan Kim and Yunmi Kim and Lee, {Dong Jin}",
year = "2017",
month = "5",
day = "3",
doi = "10.1080/00949655.2016.1262371",
language = "English",
volume = "87",
pages = "1305--1322",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "7",

}

A residual-based test for autocorrelation in quantile regression models. / Huo, Lijuan; Kim, Tae-Hwan; Kim, Yunmi; Lee, Dong Jin.

In: Journal of Statistical Computation and Simulation, Vol. 87, No. 7, 03.05.2017, p. 1305-1322.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A residual-based test for autocorrelation in quantile regression models

AU - Huo, Lijuan

AU - Kim, Tae-Hwan

AU - Kim, Yunmi

AU - Lee, Dong Jin

PY - 2017/5/3

Y1 - 2017/5/3

N2 - Quantile regression (QR) models have been increasingly employed in many applied areas in economics. At the early stage, applications in the QR literature have usually used cross-sectional data, but the recent development has seen an increase in the use of QR in both time-series and panel data sets. However, testing for possible autocorrelation, especially in the context of time-series models, has received little attention. As a rule of thumb, one might attempt to apply the usual Breusch–Godfrey LM test to the residuals of a baseline QR. In this paper, we demonstrate analytically and by Monte Carlo simulations that such an application of the LM test can result in potentially large size distortions, especially in either low or high quantiles. We then propose a correct test (named the QF test) for autocorrelation in QR models, which does not suffer from size distortion. Monte Carlo simulations demonstrate that the proposed test performs fairly well in finite samples, across either different quantiles or different underlying error distributions.

AB - Quantile regression (QR) models have been increasingly employed in many applied areas in economics. At the early stage, applications in the QR literature have usually used cross-sectional data, but the recent development has seen an increase in the use of QR in both time-series and panel data sets. However, testing for possible autocorrelation, especially in the context of time-series models, has received little attention. As a rule of thumb, one might attempt to apply the usual Breusch–Godfrey LM test to the residuals of a baseline QR. In this paper, we demonstrate analytically and by Monte Carlo simulations that such an application of the LM test can result in potentially large size distortions, especially in either low or high quantiles. We then propose a correct test (named the QF test) for autocorrelation in QR models, which does not suffer from size distortion. Monte Carlo simulations demonstrate that the proposed test performs fairly well in finite samples, across either different quantiles or different underlying error distributions.

UR - http://www.scopus.com/inward/record.url?scp=85002235302&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002235302&partnerID=8YFLogxK

U2 - 10.1080/00949655.2016.1262371

DO - 10.1080/00949655.2016.1262371

M3 - Article

VL - 87

SP - 1305

EP - 1322

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 7

ER -