Competing risks regression for clustered data - Archive ouverte HAL Access content directly
Journal Articles Biostatistics Advance Access Year : 2011

Competing risks regression for clustered data

(1) , (2) , (3) , (4)
1
2
3
4

Abstract

A population average regression model is proposed to assess the marginal effects of covariates on the cumulative incidence function when there is dependence across individuals within a cluster in the competing risks setting. This method extends the Fine?Gray model proportional hazards model for the subdistribution to situations where individualswithin a cluster may be correlated due to unobserved shared factors. Estimators of the regression parameters in the marginal model are developed under an independence working assumption, where the correlation across individuals within a cluster is completely unspecified. The estimators are consistent and asymptotically normal, and variance estimation may be achieved without specifying the form of the dependence across individuals. A simulation study evidences that the inferential procedures perform well with realistic sample sizes. The practical utility of the methods is illustrated with data from the European Bone Marrow Transplant Registry.
Not file

Dates and versions

hal-01125902 , version 1 (06-03-2015)

Identifiers

  • HAL Id : hal-01125902 , version 1

Cite

Bingqing Zhou, Jason Fine, Aurélien Latouche, Myriam Labopin. Competing risks regression for clustered data. Biostatistics Advance Access, 2011, 13, pp.371-83. ⟨hal-01125902⟩
129 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More