The identifiability of the mixed proportional hazards competing risks model
Source: Journal of the Royal Statistical Society: Series B (Statistical Methodology), Volume 65, Number 3, August 2003 , pp. 701-710(10)
We prove identification of dependent competing risks models in which each risk has a mixed proportional hazard specification with regressors, and the risks are dependent by way of the unobserved heterogeneity, or frailty, components. We show that the conditions for identification given by Heckman and Honoré can be relaxed. We extend the results to the case in which multiple spells are observed for each subject.
Document Type: Research Article
Publication date: August 1, 2003