On the Choice of Time Scales in Competing Risks Predictions

• Activity Number: 496
• Type: Contributed
• Date/Time: Wednesday, August 3, 2016 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Minjung Lee* and Natalia A. Gouskova and Eric J. Feuer and Jason Fine
• Companies: Kangwon National University and The University of North Carolina at Chapel Hill and National Cancer Institute and The University of North Carolina at Chapel Hill
• Keywords: Cumulative incidence function ; Disease registry data ; Left truncation ; Multiple time scales ; Proportional hazards model

Abstract

In the standard analysis of competing risks data, proportional hazards models are fit to the cause-specific hazard functions for all causes on the same time scale. However, in predictions arising from disease registries, where only subjects with disease enter the database, disease related mortality may be more naturally modelled on the time since diagnosis time scale while death from other causes may be more naturally modelled on the age time scale. The single time scale methodology may be biased if an incorrect time scale is employed for one of the causes and alternative methodology is not available. We propose inferences for the cumulative incidence function in which regression models for the cause-specific hazard functions may be specified on different time scales. We establish that the covariate conditional predictions are consistent and asymptotically normal using empirical process techniques and propose consistent variance estimators. The methods are illustrated with stage III colon cancer data from the SEER program of National Cancer Institute.