Statistical Modelling 9 (2009), 299–319
The regression analysis of correlated interval-censored data:
illustration using accelerated failure time models with flexible
distributional assumptions
Arnošt Komárek
Department of Probability and Mathematical Statistics
Faculty of Mathematics and Physics
Charles University in Prague
Sokolovská 83
CZ–18675 Praha 8–Karlín
Czech Republic
eMail: arnost.komarek@mff.cuni.cz
Emmanuel Lesaffre
Department of Biostatistics
Erasmus University Rotterdam
Netherlands
and
Interuniversity Institute for Biostatistics and Statistical Bioinformatics
Katholieke Universiteit Leuven and Universiteit Hasselt
Belgium.
Abstract:
The accelerated failure time (AFT) model is a useful alternative to the
proportional hazard model for modelling interval-censored survival times.
We illustrate the usefulness of a class of flexible AFT models.
Flexibility is achieved by assuming that the distributional parts consist
of penalized Gaussian mixtures. The AFT models are introduced and
exemplified via research questions originating from a longitudinal
dental study conducted in Flanders (North of Belgium). Emphasis is
put on the analyzes which are performed using routines written in the
R-language. They show the practical usefulness of our approach.
Keywords:
accelerated failure time model; interval censoring;
Markov chain Monte Carlo; paired data; random effects
Downloads:
Example data and R-code
in zipped
archive.
back