Biometrika Advance Access originally published online on January 31, 2008
Biometrika 2008 95(1):63-74; doi:10.1093/biomet/asm087
| ||||||||||||||||||||||||||||||||||||||||||||||||||
Articles |
Shared parameter models under random effects misspecification
Biostatistical Centre, Catholic University of Leuven, Kapucijnenvoer 35, B–3000 Leuven, Belgium dimitris.rizopoulos{at}med.kuleuven.be geert.verbeke{at}med.kuleuven.be
Center for Statistics, Hasselt University, Agoralaan 1, B–3590 Diepenbeek, Belgium geert.molenberghs{at}uhasselt.be
Received for publication 1 June 2006.
Revision received 1 June 2007.
| Abstract |
|---|
A common objective in longitudinal studies is the investigation of the association structure between a longitudinal response process and the time to an event of interest. An attractive paradigm for the joint modelling of longitudinal and survival processes is the shared parameter framework, where a set of random effects is assumed to induce their interdependence. In this work, we propose an alternative parameterization for shared parameter models and investigate the effect of misspecifying the random effects distribution in the parameter estimates and their standard errors.
Key Words: Copula function Dropout Joint modelling Sandwich variance estimator