Some tests for the constancy of regressions under heteroscedasticity

Hiroki Tsurumi, Neil Sheflin

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

For testing the equality of coefficients of a linear regression model under heteroscedasticity, we suggest an F criterion conditioned on the posterior mean of the ratio of standard deviations of error terms in two subsamples. For pairable subsamples, and exact F test is derived. Sampling experiments show that the Chow test differs substantially from the nominal significance level when the two subsample sizes are unequal, and that the F test conditioned on the posterior mean is superior to other tests when sample sizes are small.

Original languageEnglish (US)
Pages (from-to)221-234
Number of pages14
JournalJournal of Econometrics
Volume27
Issue number2
DOIs
StatePublished - Feb 1985

Fingerprint

Posterior Mean
F Test
Heteroscedasticity
Linear regression
Regression
Sampling
Significance level
Testing
Error term
Linear Regression Model
Unequal
Standard deviation
Categorical or nominal
Equality
Sample Size
Experiments
Coefficient
Experiment

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

@article{b97eadcafb75489aaff7bff15a20ef6b,
title = "Some tests for the constancy of regressions under heteroscedasticity",
abstract = "For testing the equality of coefficients of a linear regression model under heteroscedasticity, we suggest an F criterion conditioned on the posterior mean of the ratio of standard deviations of error terms in two subsamples. For pairable subsamples, and exact F test is derived. Sampling experiments show that the Chow test differs substantially from the nominal significance level when the two subsample sizes are unequal, and that the F test conditioned on the posterior mean is superior to other tests when sample sizes are small.",
author = "Hiroki Tsurumi and Neil Sheflin",
year = "1985",
month = "2",
doi = "https://doi.org/10.1016/0304-4076(85)90089-2",
language = "English (US)",
volume = "27",
pages = "221--234",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

Some tests for the constancy of regressions under heteroscedasticity. / Tsurumi, Hiroki; Sheflin, Neil.

In: Journal of Econometrics, Vol. 27, No. 2, 02.1985, p. 221-234.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Some tests for the constancy of regressions under heteroscedasticity

AU - Tsurumi, Hiroki

AU - Sheflin, Neil

PY - 1985/2

Y1 - 1985/2

N2 - For testing the equality of coefficients of a linear regression model under heteroscedasticity, we suggest an F criterion conditioned on the posterior mean of the ratio of standard deviations of error terms in two subsamples. For pairable subsamples, and exact F test is derived. Sampling experiments show that the Chow test differs substantially from the nominal significance level when the two subsample sizes are unequal, and that the F test conditioned on the posterior mean is superior to other tests when sample sizes are small.

AB - For testing the equality of coefficients of a linear regression model under heteroscedasticity, we suggest an F criterion conditioned on the posterior mean of the ratio of standard deviations of error terms in two subsamples. For pairable subsamples, and exact F test is derived. Sampling experiments show that the Chow test differs substantially from the nominal significance level when the two subsample sizes are unequal, and that the F test conditioned on the posterior mean is superior to other tests when sample sizes are small.

UR - http://www.scopus.com/inward/record.url?scp=0041392799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041392799&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/0304-4076(85)90089-2

DO - https://doi.org/10.1016/0304-4076(85)90089-2

M3 - Article

VL - 27

SP - 221

EP - 234

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -