Online Program

WITHDRAWN: Copula-Based Semiparametric Multivariate Frailty Models for Multi-Type Recurrent Event Data and an Application to Cancer Prevention Trial

Khaled F. Bedair, PhD , Assistant Professor. 
Yili Hong, PhD, Associate Professor 

Keywords: Copula functions, Correlated frailty, MCMC, Proportional hazards model, Random effects, MCEM algorithm, Skin cancer

Multi-type recurrent event data arise in many situations when two or more different event types may occur repeatedly over an observation period. We propose the use of proportional intensity models with multivariate frailty terms to model such data. The proposed models can take into account the dependence among different event types within a subject, as well as the effect of covariates. More flexible approaches to modeling the correlated frailty terms referred to as copula functions are introduced. Copula functions provide tremendous flexibility, especially in allowing one to take advantage of a variety of choices for the marginal distributions and correlation structures. Maximum likelihood estimates of the regression coefficients, variance-covariance components, and the nonparametric baseline intensity function are obtained via a Monte Carlo Expectation Maximization (MCEM) algorithm. The E step of the algorithm involves the calculation of the conditional expectations of the frailty terms by using the Metropolis-Hastings sampling. Simulation studies were used to validate the performance of the proposed method, followed by an application to the skin cancer prevention data.