Grouped Time-Transformation Model with Sterile Fraction: An Application to Time to Pregnancy

• Activity Number: 224
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Alexander McLain*+ and Rajeshwari Sundaram
• Companies: National Institutes of Health and Eunice Kennedy Shriver National Institute of Child Health and Human Development
• Keywords: Survival Analysis ; Grouped Data ; Transformation Model ; Estimating Equations

Abstract

Many interesting statistical issues arise when analyzing time to pregnancy, the number of menstrual cycles it takes a couple to become pregnant, or TTP data. Scheike and Jensen (1997) proposed using the discrete time equivalent to the proportional hazards model to analyzing TTP data. While the discrete survival approach has had some success in the TTP literature, some have critiqued its lack of biological validity. Current discrete survival models do not allow for the incorporation of day-level behavioral effects that occur within the `fertile window'. In this paper, we propose a flexible class of grouped time-transformation cure models that addresses biological validity by allowing day-level covariates and coefficients to be included. Asymptotic properties are illustrated. The performance of our method is demonstrated on simulated and real data.