A note on including time-dependent covariate in regression model for competing risks data.

Biometrical journal. Biometrische Zeitschrift ·Vol. 47 ·No. 6 ·2005-12-00 ·Pages 807-14

Latouche A, Porcher R, Chevret S

Abstract

Recently, regression analysis of the cumulative incidence function has gained interest in competing risks data analysis, through the model proposed by Fine and Gray (JASA 1999; 94: 496-509). In this note, we point out that inclusion of time-dependent covariates in this model can lead to serious bias. We illustrate the problems arising in such a context, using bone marrow transplant data as a working example and numerical simulations. Practical advices are given, preventing the misuse of this model.

MeSH Terms

Algorithms Analysis of Variance Bias Bone Marrow Transplantation/mortality,statistics & numerical data Child Graft vs Host Disease/mortality Humans Leukemia/therapy Longitudinal Studies Models, Statistical Monte Carlo Method Probability Proportional Hazards Models Recurrence Regression Analysis Risk Assessment/statistics & numerical data Survival Analysis Survival Rate

Authors & Affiliations

3 authors, click to expand affiliations / ORCID

Latouche A

Département de Biostatistique et Informatique Médicale, Hôpital Saint-Louis, AP-HP, Inserm U717, F-75010 Paris, France. aurelien.latouche@paris7.jussieu.fr

Porcher R

Chevret S

Article Info

Journal

Biometrical journal. Biometrische Zeitschrift

Abbr.

Biom J

ISSN

0323-3847

DOI

10.1002/bimj.200410152

aurelien.latouche@paris7.jussieu.fr

Published

2005-12-00

Pages

807-14

Language

English

Region

Germany

NLM ID

7708048

Subset

External Links

PubMed source DOI: 10.1002/bimj.200410152 View journal details

Analysis Services

A note on including time-dependent covariate in regression model for competing risks data.

Contact

WeChat Official Account