Generalized empirical likelihood methods for analyzing longitudinal data

Handle URI:
http://hdl.handle.net/10754/598400
Title:
Generalized empirical likelihood methods for analyzing longitudinal data
Authors:
Wang, S.; Qian, L.; Carroll, R. J.
Abstract:
Efficient estimation of parameters is a major objective in analyzing longitudinal data. We propose two generalized empirical likelihood based methods that take into consideration within-subject correlations. A nonparametric version of the Wilks theorem for the limiting distributions of the empirical likelihood ratios is derived. It is shown that one of the proposed methods is locally efficient among a class of within-subject variance-covariance matrices. A simulation study is conducted to investigate the finite sample properties of the proposed methods and compare them with the block empirical likelihood method by You et al. (2006) and the normal approximation with a correctly estimated variance-covariance. The results suggest that the proposed methods are generally more efficient than existing methods which ignore the correlation structure, and better in coverage compared to the normal approximation with correctly specified within-subject correlation. An application illustrating our methods and supporting the simulation study results is also presented.
Citation:
Wang S, Qian L, Carroll RJ (2010) Generalized empirical likelihood methods for analyzing longitudinal data. Biometrika 97: 79–93. Available: http://dx.doi.org/10.1093/biomet/asp073.
Publisher:
Oxford University Press (OUP)
Journal:
Biometrika
Issue Date:
16-Feb-2010
DOI:
10.1093/biomet/asp073
PubMed ID:
20305730
PubMed Central ID:
PMC2841365
Type:
Article
ISSN:
0006-3444; 1464-3510
Sponsors:
We thank the editor, the associate editor and two referees for their helpful comments and suggestionsthat have led to significant improvements of this paper. Carroll’s research was supportedby a grant from the National Cancer Institute and by a research award made by the King AbdullahUniversity of Science and Technology.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorWang, S.en
dc.contributor.authorQian, L.en
dc.contributor.authorCarroll, R. J.en
dc.date.accessioned2016-02-25T13:20:04Zen
dc.date.available2016-02-25T13:20:04Zen
dc.date.issued2010-02-16en
dc.identifier.citationWang S, Qian L, Carroll RJ (2010) Generalized empirical likelihood methods for analyzing longitudinal data. Biometrika 97: 79–93. Available: http://dx.doi.org/10.1093/biomet/asp073.en
dc.identifier.issn0006-3444en
dc.identifier.issn1464-3510en
dc.identifier.pmid20305730en
dc.identifier.doi10.1093/biomet/asp073en
dc.identifier.urihttp://hdl.handle.net/10754/598400en
dc.description.abstractEfficient estimation of parameters is a major objective in analyzing longitudinal data. We propose two generalized empirical likelihood based methods that take into consideration within-subject correlations. A nonparametric version of the Wilks theorem for the limiting distributions of the empirical likelihood ratios is derived. It is shown that one of the proposed methods is locally efficient among a class of within-subject variance-covariance matrices. A simulation study is conducted to investigate the finite sample properties of the proposed methods and compare them with the block empirical likelihood method by You et al. (2006) and the normal approximation with a correctly estimated variance-covariance. The results suggest that the proposed methods are generally more efficient than existing methods which ignore the correlation structure, and better in coverage compared to the normal approximation with correctly specified within-subject correlation. An application illustrating our methods and supporting the simulation study results is also presented.en
dc.description.sponsorshipWe thank the editor, the associate editor and two referees for their helpful comments and suggestionsthat have led to significant improvements of this paper. Carroll’s research was supportedby a grant from the National Cancer Institute and by a research award made by the King AbdullahUniversity of Science and Technology.en
dc.publisherOxford University Press (OUP)en
dc.subjectConfidence regionen
dc.subjectEfficient estimationen
dc.subjectEmpirical likelihooden
dc.subjectLongitudinal dataen
dc.subjectMaximum empirical likelihood estimatoren
dc.titleGeneralized empirical likelihood methods for analyzing longitudinal dataen
dc.typeArticleen
dc.identifier.journalBiometrikaen
dc.identifier.pmcidPMC2841365en
dc.contributor.institutionDepartment of Statistics, Texas A&M University, College Station, Texas 77843, U.S.A.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.