Please use this identifier to cite or link to this item: https://doi.org/10.1093/biomet/asm007
DC FieldValue
dc.titleEstimation of a covariance matrix with zeros
dc.contributor.authorChaudhuri, S.
dc.contributor.authorDrton, M.
dc.contributor.authorRichardson, T.S.
dc.date.accessioned2014-10-28T05:11:56Z
dc.date.available2014-10-28T05:11:56Z
dc.date.issued2007-03
dc.identifier.citationChaudhuri, S., Drton, M., Richardson, T.S. (2007-03). Estimation of a covariance matrix with zeros. Biometrika 94 (1) : 199-216. ScholarBank@NUS Repository. https://doi.org/10.1093/biomet/asm007
dc.identifier.issn00063444
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/105131
dc.description.abstractWe consider estimation of the covariance matrix of a multivariate random vector under the constraint that certain covariances are zero. We first present an algorithm, which we call iterative conditional fitting, for computing the maximum likelihood estimate of the constrained covariance matrix, under the assumption of multivariate normality. In contrast to previous approaches, this algorithm has guaranteed convergence properties. Dropping the assumption of multivariate normality, we show how to estimate the covariance matrix in an empirical likelihood approach. These approaches are then compared via simulation and on an example of gene expression. © 2007 Biometrika Trust.
dc.sourceScopus
dc.subjectCovariance graph
dc.subjectEmpirical likelihood
dc.subjectGraphical model
dc.subjectMarginal independence
dc.subjectMaximum likelihood estimation
dc.subjectMultivariate normal distribution
dc.typeArticle
dc.contributor.departmentSTATISTICS & APPLIED PROBABILITY
dc.description.doi10.1093/biomet/asm007
dc.description.sourcetitleBiometrika
dc.description.volume94
dc.description.issue1
dc.description.page199-216
dc.description.codenBIOKA
dc.identifier.isiut000244839800014
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

68
checked on Nov 30, 2021

WEB OF SCIENCETM
Citations

64
checked on Nov 30, 2021

Page view(s)

114
checked on Dec 2, 2021

Google ScholarTM

Check

Altmetric


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