Testing for random effects in linear mixed models for longitudinal data under moment conditions

Zai Xing Li; Lixing ZHU; Ping Wu; Jian Hong Wu; Wang Li Xu

doi:10.1007/s10114-010-8502-z

Testing for random effects in linear mixed models for longitudinal data under moment conditions

Zai Xing Li, Lixing ZHU, Ping Wu, Jian Hong Wu, Wang Li Xu

Department of Mathematics

Research output: Contribution to journal › Journal article › peer-review

2 Citations (Scopus)

Abstract

In this paper, we consider whether the random effect exists in linear mixed models (LMMs) when only moment conditions are assumed. Based on the estimators of parameters and their asymptotic properties, a Wald-type test is constructed. It is consistent against global alternatives and is sensitive to the local alternatives converging to the null hypothesis at parametric rates, a fastest possibly rate for goodness-of-fit testing. Moreover, a simulation study shows the performance of the test is good. The procedure also applies to a real data.

Original language	English
Pages (from-to)	497-514
Number of pages	18
Journal	Acta Mathematica Sinica, English Series
Volume	26
Issue number	3
DOIs	https://doi.org/10.1007/s10114-010-8502-z
Publication status	Published - Mar 2010

Scopus Subject Areas

Mathematics(all)
Applied Mathematics

User-Defined Keywords

Asymptotic normality
Consistent estimators
LMMs
Random effects

Access to Document

10.1007/s10114-010-8502-z

Cite this

@article{066bb4db631644a69928260dbfebbc8c,

title = "Testing for random effects in linear mixed models for longitudinal data under moment conditions",

abstract = "In this paper, we consider whether the random effect exists in linear mixed models (LMMs) when only moment conditions are assumed. Based on the estimators of parameters and their asymptotic properties, a Wald-type test is constructed. It is consistent against global alternatives and is sensitive to the local alternatives converging to the null hypothesis at parametric rates, a fastest possibly rate for goodness-of-fit testing. Moreover, a simulation study shows the performance of the test is good. The procedure also applies to a real data.",

keywords = "Asymptotic normality, Consistent estimators, LMMs, Random effects",

author = "Li, {Zai Xing} and Lixing ZHU and Ping Wu and Wu, {Jian Hong} and Xu, {Wang Li}",

note = "Funding Information: Received October 9, 2008, Accepted May 18, 2009 Supported by a grant (HKBU2030/07P) from the Research Grants Council of Hong Kong, the National Natural Science Foundation of China (Grant No. 10871001), the Humanities and Social Sciences Project of Chinese Ministry of Education (Grant No. 08JC910002), Zhejiang Provincial Natural Science Foundation of China (Grant No. Y6090172) and Youth Talent Foundation of Zhejiang Gongshang University, China",

year = "2010",

month = mar,

doi = "10.1007/s10114-010-8502-z",

language = "English",

volume = "26",

pages = "497--514",

journal = "Acta Mathematica Sinica, English Series",

issn = "1439-8516",

publisher = "Springer Verlag",

number = "3",

}

TY - JOUR

T1 - Testing for random effects in linear mixed models for longitudinal data under moment conditions

AU - Li, Zai Xing

AU - ZHU, Lixing

AU - Wu, Ping

AU - Wu, Jian Hong

AU - Xu, Wang Li

N1 - Funding Information: Received October 9, 2008, Accepted May 18, 2009 Supported by a grant (HKBU2030/07P) from the Research Grants Council of Hong Kong, the National Natural Science Foundation of China (Grant No. 10871001), the Humanities and Social Sciences Project of Chinese Ministry of Education (Grant No. 08JC910002), Zhejiang Provincial Natural Science Foundation of China (Grant No. Y6090172) and Youth Talent Foundation of Zhejiang Gongshang University, China

PY - 2010/3

Y1 - 2010/3

N2 - In this paper, we consider whether the random effect exists in linear mixed models (LMMs) when only moment conditions are assumed. Based on the estimators of parameters and their asymptotic properties, a Wald-type test is constructed. It is consistent against global alternatives and is sensitive to the local alternatives converging to the null hypothesis at parametric rates, a fastest possibly rate for goodness-of-fit testing. Moreover, a simulation study shows the performance of the test is good. The procedure also applies to a real data.

AB - In this paper, we consider whether the random effect exists in linear mixed models (LMMs) when only moment conditions are assumed. Based on the estimators of parameters and their asymptotic properties, a Wald-type test is constructed. It is consistent against global alternatives and is sensitive to the local alternatives converging to the null hypothesis at parametric rates, a fastest possibly rate for goodness-of-fit testing. Moreover, a simulation study shows the performance of the test is good. The procedure also applies to a real data.

KW - Asymptotic normality

KW - Consistent estimators

KW - LMMs

KW - Random effects

UR - http://www.scopus.com/inward/record.url?scp=77952866924&partnerID=8YFLogxK

U2 - 10.1007/s10114-010-8502-z

DO - 10.1007/s10114-010-8502-z

M3 - Journal article

AN - SCOPUS:77952866924

SN - 1439-8516

VL - 26

SP - 497

EP - 514

JO - Acta Mathematica Sinica, English Series

JF - Acta Mathematica Sinica, English Series

IS - 3

ER -

Testing for random effects in linear mixed models for longitudinal data under moment conditions

Abstract

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this