Estimating Regression Parameters and Degree of Dependence for Multivariate Failure Time Data
Version of Record online: 25 MAY 2004
Volume 55, Issue 4, pages 1078–1084, December 1999
How to Cite
Mahé, C. and Chevret, S. (1999), Estimating Regression Parameters and Degree of Dependence for Multivariate Failure Time Data. Biometrics, 55: 1078–1084. doi: 10.1111/j.0006-341X.1999.01078.x
- Issue online: 25 MAY 2004
- Version of Record online: 25 MAY 2004
- Received June 1997. Revised March 1999. Accepted March 1999.
- Counting processes;
- Frailty model;
- Marginal hazards model;
- Multivariate failure time data;
- Proportional hazards model
Summary. Multivariate failure time data are frequently encountered in longitudinal studies when subjects may experience several events or when there is a grouping of individuals into a cluster. To take into account the dependence of the failure times within the unit (the individual or the cluster) as well as censoring, two multivariate generalizations of the Cox proportional hazards model are commonly used. The marginal hazard model is used when the purpose is to estimate mean regression parameters, while the frailty model is retained when the purpose is to assess the degree of dependence within the unit. We propose a new approach based on the combination of the two aforementioned models to estimate both these quantities. This two-step estimation procedure is quicker and more simple to implement than the EM algorithm used in frailty models estimation. Simulation results are provided to illustrate robustness, consistency, and large-sample properties of estimators. Finally, this method is exemplified on a diabetic retinopathy study in order to assess the effect of photocoagulation in delaying the onset of blindness as well as the dependence between the two eyes blindness times of a patient.