Joint Modeling Approach for Semicompeting Risks Data with Missing Nonterminal Event Status

• Activity Number: 130
• Type: Contributed
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Chen Hu*+ and Alex Tsodikov
• Companies: and University of Michigan
• Keywords: Semicompeting risks ; Multistate model ; Proportional hazards ; Dependent censoring ; Missing data ; Survival analysis

Abstract

Semicompeting risks data, where a subject may experience sequential nonterminal and terminal events, and the terminal event may censor the nonterminal event but not vice verse, are widely available in many biomedical studies. We consider the situation when a proportion of subjects' nonterminal event is missing, such that the observed data become a mixture of ``true' semicompeting risks data and partially observed terminal event only data. An illness-death multistate model with proportional hazards assumptions is proposed to identify the relationship between nonterminal and terminal events, and provides covariate-specific Kendall's $\tau$ for dependence measure. Maximum likelihood estimation based on semiparametric regression analysis is used for statistical inference, and asymptotic properties of proposed estimators are studied using martingale theory. We illustrate the proposed method with simulation studies and data analysis of a follicular cell lymphoma study.