A linear mixed-effects model for multivariate censored data

Authors
Pan, W Louis, TA
Citation
W. Pan et Ta. Louis, A linear mixed-effects model for multivariate censored data, BIOMETRICS, 56(1), 2000, pp. 160-166
Citations number
23
Categorie Soggetti
Biology,Multidisciplinary
Journal title
BIOMETRICS
ISSN journal
0006341X → ACNP
Volume
56
Issue
1
Year of publication
2000
Pages
160 - 166
Database
ISI
SICI code
0006-341X(200003)56:1<160:ALMMFM>2.0.ZU;2-0
Abstract
We apply a linear mixed-effects model to multivariate failure time data. Co mputation of the regression parameters involves the Buckley-James method in an iterated Monte Carlo expectation-maximization algorithm, wherein the Mo nte Carlo E-step is implemented using the Metropolis-Hastings algorithm. Fr om simulation studies, this approach compares favorably with the marginal i ndependence approach, especially when there is a strong within-cluster corr elation.