A0321
Title: Bivariate copula regression models for semi-competing risks with application to kidney transplant data
Authors: Malgorzata Wojtys - University of Plymouth (United Kingdom) [presenting]
Yinghui Wei - Plymouth University (United Kingdom)
Lexy Sorrell - University of Plymouth (United Kingdom)
Peter Rowe - University Hospitals Plymouth NHS Trust (United Kingdom)
Abstract: Time-to-event semi-competing risk endpoints may be correlated when both events occur on the same individual. These events and the association between them may also be influenced by individual characteristics. Copula survival models are considered to estimate hazard ratios of covariates on the non-terminal and terminal events, along with the effects of covariates on the association between the two events. A novel application of the proposed methods is presented to model semi-competing risks of graft failure and death for kidney transplant patients from the United Kingdom Transplant Registry, held by the National Health Service Blood and Transplant. The Normal, Clayton, Frank and Gumbel copulas are used to provide a variety of association structures between the non-terminal and terminal events. It is found that copula survival models perform better than the Cox proportional hazards model when estimating the non-terminal event hazard ratio of covariates. It is also found that the inclusion of covariates in the association parameter of the copula models improves the estimation of the hazard ratios. Moreover, results of a simulation study exploring the effects of model miss-specification are presented.