Joint Modeling of Longitudinal Outcomes and Discrete Survival Times Using a Copula

• Activity Number: 562
• Type: Contributed
• Date/Time: Wednesday, August 6, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Shuling Liu*+ and Amita K. Manatunga and Limin Peng
• Companies: Emory University and Emory University and Emory University
• Keywords: Clayton-Oakes model ; maximum likelihood ; joint modeling ; menstrual cycle length ; time-to-pregnancy

Abstract

We propose a joint modeling approach to study a longitudinal response and a discrete time-to-event endpoint for situations where the longitudinal response is subject to data complications such as missing, censoring and truncation. This work is motivated by the Mount Sinai Study of Women Office Workers (MSSWOW) in which women were prospectively followed for one year in order to study fertility. For each woman, menstrual cycle lengths are recorded until time-to-pregnancy (TTP) or the end of study. Repeated menstrual cycle lengths are modeled by the Clayton-Oakes multivariate survival model with the dimension indexed by TTP. To investigate the covariate effects, we appropriately parameterize the marginal distributions of the Clayton-Oakes model, the association between menstrual cycle lengths, and the distribution of TTP in terms of the covariates. Maximum likelihood estimation is considered while handling missing, censoring, and left truncation on both outcomes. Simulation studies are conducted to evaluate the performance of the proposed joint modeling procedure. Finally we apply our method to MSSWOW data.