Please use this identifier to cite or link to this item: https://doi.org/10.1002/cjs.10129
DC FieldValue
dc.titleImproving variance function estimation in semiparametric longitudinal data analysis
dc.contributor.authorLeng, C.
dc.contributor.authorTang, C.Y.
dc.date.accessioned2014-10-28T05:12:40Z
dc.date.available2014-10-28T05:12:40Z
dc.date.issued2011-12
dc.identifier.citationLeng, C., Tang, C.Y. (2011-12). Improving variance function estimation in semiparametric longitudinal data analysis. Canadian Journal of Statistics 39 (4) : 656-670. ScholarBank@NUS Repository. https://doi.org/10.1002/cjs.10129
dc.identifier.issn03195724
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/105178
dc.description.abstractWe propose an efficient and robust method for variance function estimation in semiparametric longitudinal data analysis. The method utilizes a local log-linear approximation for the variance function and adopts a generalized estimating equation approach to account for within subject correlations. We show theoretically and empirically that our method outperforms estimators using working independence that ignores the correlations. © 2011 Statistical Society of Canada.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1002/cjs.10129
dc.sourceScopus
dc.subjectAsymptotic relative efficiency
dc.subjectLocal linear estimator
dc.subjectLongitudinal data analysis
dc.subjectVariance function estimation
dc.typeArticle
dc.contributor.departmentSTATISTICS & APPLIED PROBABILITY
dc.description.doi10.1002/cjs.10129
dc.description.sourcetitleCanadian Journal of Statistics
dc.description.volume39
dc.description.issue4
dc.description.page656-670
dc.identifier.isiut000297112900006
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

3
checked on Aug 18, 2022

WEB OF SCIENCETM
Citations

3
checked on Aug 18, 2022

Page view(s)

143
checked on Aug 18, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.