A semiparametric likelihood approach to joint modeling of longitudinal and time-to-event data.

Journal Article (Journal Article)

Joint models for a time-to-event (e.g., survival) and a longitudinal response have generated considerable recent interest. The longitudinal data are assumed to follow a mixed effects model, and a proportional hazards model depending on the longitudinal random effects and other covariates is assumed for the survival endpoint. Interest may focus on inference on the longitudinal data process, which is informatively censored, or on the hazard relationship. Several methods for fitting such models have been proposed, most requiring a parametric distributional assumption (normality) on the random effects. A natural concern is sensitivity to violation of this assumption; moreover, a restrictive distributional assumption may obscure key features in the data. We investigate these issues through our proposal of a likelihood-based approach that requires only the assumption that the random effects have a smooth density. Implementation via the EM algorithm is described, and performance and the benefits for uncovering noteworthy features are illustrated by application to data from an HIV clinical trial and by simulation.

Full Text

Duke Authors

Cited Authors

  • Song, X; Davidian, M; Tsiatis, AA

Published Date

  • December 2002

Published In

Volume / Issue

  • 58 / 4

Start / End Page

  • 742 - 753

PubMed ID

  • 12495128

International Standard Serial Number (ISSN)

  • 0006-341X

Digital Object Identifier (DOI)

  • 10.1111/j.0006-341x.2002.00742.x


  • eng

Conference Location

  • United States