Testing for serial correlation in multivariate regression models

Aikaterini Kyriazidou

Research output: Contribution to journalArticle

Abstract

This paper considers the problem of detecting serial correlation in the disturbances of a multivariate regression model, when these are known to be correlated up to a known finite lag Q ≥ 0 and are possibly conditionally heteroskedastic. We extend the results of Cumby and Huizinga (1992) to the case of a linear dynamic system of equations, and derive the asymptotic distribution of a vector of sample autocovariances of the regression residuals. This distribution is used to construct a test for serial correlation at lags greater than Q. A comparative Monte Carlo study of the small-sample behavior of various tests in the case of purely autoregressive series reveals that the proposed test performs satisfactorily, while tests that are commonly used in the literature are found to lead to serious size distortions under conditional heteroskedasticity.

Original languageEnglish (US)
Pages (from-to)193-220
Number of pages28
JournalJournal of Econometrics
Volume86
Issue number2
DOIs
StatePublished - Jun 16 1998

Fingerprint

Regression model
Multivariate regression
Serial correlation
Testing
Lag
Conditional heteroskedasticity
Asymptotic distribution
Size distortion
Dynamic systems
Small sample
Monte Carlo study

Keywords

  • Conditional heteroskedasticity
  • Multivariate regression
  • Serial correlation

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Testing for serial correlation in multivariate regression models. / Kyriazidou, Aikaterini.

In: Journal of Econometrics, Vol. 86, No. 2, 16.06.1998, p. 193-220.

Research output: Contribution to journalArticle

Kyriazidou, Aikaterini. / Testing for serial correlation in multivariate regression models. In: Journal of Econometrics. 1998 ; Vol. 86, No. 2. pp. 193-220.
@article{4ab5913e1f2f478c956ee317582dc1fb,
title = "Testing for serial correlation in multivariate regression models",
abstract = "This paper considers the problem of detecting serial correlation in the disturbances of a multivariate regression model, when these are known to be correlated up to a known finite lag Q ≥ 0 and are possibly conditionally heteroskedastic. We extend the results of Cumby and Huizinga (1992) to the case of a linear dynamic system of equations, and derive the asymptotic distribution of a vector of sample autocovariances of the regression residuals. This distribution is used to construct a test for serial correlation at lags greater than Q. A comparative Monte Carlo study of the small-sample behavior of various tests in the case of purely autoregressive series reveals that the proposed test performs satisfactorily, while tests that are commonly used in the literature are found to lead to serious size distortions under conditional heteroskedasticity.",
keywords = "Conditional heteroskedasticity, Multivariate regression, Serial correlation",
author = "Aikaterini Kyriazidou",
year = "1998",
month = "6",
day = "16",
doi = "10.1016/S0304-4076(97)00114-0",
language = "English (US)",
volume = "86",
pages = "193--220",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

TY - JOUR

T1 - Testing for serial correlation in multivariate regression models

AU - Kyriazidou, Aikaterini

PY - 1998/6/16

Y1 - 1998/6/16

N2 - This paper considers the problem of detecting serial correlation in the disturbances of a multivariate regression model, when these are known to be correlated up to a known finite lag Q ≥ 0 and are possibly conditionally heteroskedastic. We extend the results of Cumby and Huizinga (1992) to the case of a linear dynamic system of equations, and derive the asymptotic distribution of a vector of sample autocovariances of the regression residuals. This distribution is used to construct a test for serial correlation at lags greater than Q. A comparative Monte Carlo study of the small-sample behavior of various tests in the case of purely autoregressive series reveals that the proposed test performs satisfactorily, while tests that are commonly used in the literature are found to lead to serious size distortions under conditional heteroskedasticity.

AB - This paper considers the problem of detecting serial correlation in the disturbances of a multivariate regression model, when these are known to be correlated up to a known finite lag Q ≥ 0 and are possibly conditionally heteroskedastic. We extend the results of Cumby and Huizinga (1992) to the case of a linear dynamic system of equations, and derive the asymptotic distribution of a vector of sample autocovariances of the regression residuals. This distribution is used to construct a test for serial correlation at lags greater than Q. A comparative Monte Carlo study of the small-sample behavior of various tests in the case of purely autoregressive series reveals that the proposed test performs satisfactorily, while tests that are commonly used in the literature are found to lead to serious size distortions under conditional heteroskedasticity.

KW - Conditional heteroskedasticity

KW - Multivariate regression

KW - Serial correlation

UR - http://www.scopus.com/inward/record.url?scp=0347335538&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0347335538&partnerID=8YFLogxK

U2 - 10.1016/S0304-4076(97)00114-0

DO - 10.1016/S0304-4076(97)00114-0

M3 - Article

VL - 86

SP - 193

EP - 220

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -