The asymptotic distribution of the F-test statistic for individual effects

C.D. Orme; T. Yamagata

doi:10.1111/j.1368-423X.2006.00191.x

The asymptotic distribution of the F-test statistic for individual effects

C.D. Orme, T. Yamagata

Economics

Research output: Contribution to journal › Article › peer-review

Abstract

This paper employs first-order asymptotic theory in order to establish the asymptotic distribution of the F-test statistic for fixed effects, under non-normality of the errors, when N¿8 (the number of cross-sections) and T is fixed (the number of time periods). Three theoretical results emerge: (i) the standard F-test procedure will still deliver asymptotically valid inferences; (ii) under (pure) local random effects, the F-test and random effects test procedures have identical asymptotic power; (iii) under local fixed, or random effects which are correlated with the regressors, the F-test will have higher asymptotic power than the random effects test.

Original language	English
Pages (from-to)	404-422
Number of pages	18
Journal	Econometrics Journal
Volume	9
Issue number	3
DOIs	https://doi.org/10.1111/j.1368-423X.2006.00191.x
Publication status	Published - Sept 2006

Access to Document

10.1111/j.1368-423X.2006.00191.x

http://dx.doi.org/10.1111/j.1368-423X.2006.00191.x

Cite this

@article{9758388313b748fdaa360c7ed69d81d4,

title = "The asymptotic distribution of the F-test statistic for individual effects",

abstract = "This paper employs first-order asymptotic theory in order to establish the asymptotic distribution of the F-test statistic for fixed effects, under non-normality of the errors, when N¿8 (the number of cross-sections) and T is fixed (the number of time periods). Three theoretical results emerge: (i) the standard F-test procedure will still deliver asymptotically valid inferences; (ii) under (pure) local random effects, the F-test and random effects test procedures have identical asymptotic power; (iii) under local fixed, or random effects which are correlated with the regressors, the F-test will have higher asymptotic power than the random effects test.",

author = "C.D. Orme and T. Yamagata",

year = "2006",

month = sep,

doi = "10.1111/j.1368-423X.2006.00191.x",

language = "English",

volume = "9",

pages = "404--422",

journal = "Econometrics Journal",

issn = "1368-4221",

publisher = "Wiley-Blackwell",

number = "3",

}

TY - JOUR

T1 - The asymptotic distribution of the F-test statistic for individual effects

AU - Orme, C.D.

AU - Yamagata, T.

PY - 2006/9

Y1 - 2006/9

N2 - This paper employs first-order asymptotic theory in order to establish the asymptotic distribution of the F-test statistic for fixed effects, under non-normality of the errors, when N¿8 (the number of cross-sections) and T is fixed (the number of time periods). Three theoretical results emerge: (i) the standard F-test procedure will still deliver asymptotically valid inferences; (ii) under (pure) local random effects, the F-test and random effects test procedures have identical asymptotic power; (iii) under local fixed, or random effects which are correlated with the regressors, the F-test will have higher asymptotic power than the random effects test.

AB - This paper employs first-order asymptotic theory in order to establish the asymptotic distribution of the F-test statistic for fixed effects, under non-normality of the errors, when N¿8 (the number of cross-sections) and T is fixed (the number of time periods). Three theoretical results emerge: (i) the standard F-test procedure will still deliver asymptotically valid inferences; (ii) under (pure) local random effects, the F-test and random effects test procedures have identical asymptotic power; (iii) under local fixed, or random effects which are correlated with the regressors, the F-test will have higher asymptotic power than the random effects test.

U2 - 10.1111/j.1368-423X.2006.00191.x

DO - 10.1111/j.1368-423X.2006.00191.x

M3 - Article

SN - 1368-4221

VL - 9

SP - 404

EP - 422

JO - Econometrics Journal

JF - Econometrics Journal

IS - 3

ER -