Wild-bootstrapped variance-ratio test for autocorrelation in the presence of heteroskedasticity

Jinook Jeong, Byunguk Kang

Research output: Contribution to journalArticle

Abstract

The Breusch-Godfrey LM test is one of the most popular tests for autocorrelation. However, it has been shown that the LM test may be erroneous when there exist heteroskedastic errors in a regression model. Recently, remedies have been proposed by Godfrey and Tremayne [9] and Shim et al. [21]. This paper suggests three wild-bootstrapped variance-ratio (WB-VR) tests for autocorrelation in the presence of heteroskedasticity. We show through a Monte Carlo simulation that our WB-VR tests have better small sample properties and are robust to the structure of heteroskedasticity.

Original languageEnglish
Pages (from-to)1531-1542
Number of pages12
JournalJournal of Applied Statistics
Volume39
Issue number7
DOIs
Publication statusPublished - 2012 Jul 1

Fingerprint

Ratio test
Variance Ratio
Heteroskedasticity
Autocorrelation
Small Sample
Regression Model
Monte Carlo Simulation
LM test
Variance ratio test
Regression model
Remedies
Monte Carlo simulation
Small sample properties

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{c52a5907ca3541e1bd29cbcbe49ad780,
title = "Wild-bootstrapped variance-ratio test for autocorrelation in the presence of heteroskedasticity",
abstract = "The Breusch-Godfrey LM test is one of the most popular tests for autocorrelation. However, it has been shown that the LM test may be erroneous when there exist heteroskedastic errors in a regression model. Recently, remedies have been proposed by Godfrey and Tremayne [9] and Shim et al. [21]. This paper suggests three wild-bootstrapped variance-ratio (WB-VR) tests for autocorrelation in the presence of heteroskedasticity. We show through a Monte Carlo simulation that our WB-VR tests have better small sample properties and are robust to the structure of heteroskedasticity.",
author = "Jinook Jeong and Byunguk Kang",
year = "2012",
month = "7",
day = "1",
doi = "10.1080/02664763.2012.658360",
language = "English",
volume = "39",
pages = "1531--1542",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "7",

}

Wild-bootstrapped variance-ratio test for autocorrelation in the presence of heteroskedasticity. / Jeong, Jinook; Kang, Byunguk.

In: Journal of Applied Statistics, Vol. 39, No. 7, 01.07.2012, p. 1531-1542.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Wild-bootstrapped variance-ratio test for autocorrelation in the presence of heteroskedasticity

AU - Jeong, Jinook

AU - Kang, Byunguk

PY - 2012/7/1

Y1 - 2012/7/1

N2 - The Breusch-Godfrey LM test is one of the most popular tests for autocorrelation. However, it has been shown that the LM test may be erroneous when there exist heteroskedastic errors in a regression model. Recently, remedies have been proposed by Godfrey and Tremayne [9] and Shim et al. [21]. This paper suggests three wild-bootstrapped variance-ratio (WB-VR) tests for autocorrelation in the presence of heteroskedasticity. We show through a Monte Carlo simulation that our WB-VR tests have better small sample properties and are robust to the structure of heteroskedasticity.

AB - The Breusch-Godfrey LM test is one of the most popular tests for autocorrelation. However, it has been shown that the LM test may be erroneous when there exist heteroskedastic errors in a regression model. Recently, remedies have been proposed by Godfrey and Tremayne [9] and Shim et al. [21]. This paper suggests three wild-bootstrapped variance-ratio (WB-VR) tests for autocorrelation in the presence of heteroskedasticity. We show through a Monte Carlo simulation that our WB-VR tests have better small sample properties and are robust to the structure of heteroskedasticity.

UR - http://www.scopus.com/inward/record.url?scp=84861856975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861856975&partnerID=8YFLogxK

U2 - 10.1080/02664763.2012.658360

DO - 10.1080/02664763.2012.658360

M3 - Article

AN - SCOPUS:84861856975

VL - 39

SP - 1531

EP - 1542

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 7

ER -