B1007
Title: Joint regression analysis for survival data in the presence of two semi-competing risks
Authors: Mengjiao Peng - Nangyang Technological University (Singapore) [presenting]
Abstract: Unlike the usual semi-competing risks setting that includes two types of events: the nonterminal and terminal events, in some clinical studies with complex disease process individuals may be at risk of several different types of clinical events. We consider a situation in which three events: two nonterminal events and one terminal event are of interest. This is the case of our motivating bone marrow transplant study in which individuals may experience the acute Graft-Versus-host disease (GvHD), relapse and death after an allogeneic transplant, where the GvHD is associated with the relapse free survival, both the GVHD and relapse are intermediate nonterminal events subject to dependent censoring by the informative terminal event death, but not vice versa. We propose a novel statistical approach that jointly models times to these three types of events using a pair of copulas to account for dependence structures, while each marginal distribution of the event times is formulated by a Cox proportional hazards model. We develop an estimation procedure based on pseudo likelihood and carry out simulation studies to examine the performance of the proposed method in finite samples. The practical utility of the proposed methodology is further illustrated with data from the motivating example on bone marrow transplant.
