Imputation Methods for Semiparametric Modeling of the Subdistribution Hazard

• Activity Number: 531
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Ludi Fan*+ and Douglas Earl Schaubel
• Companies: University of Michigan and University of Michigan
• Keywords: censoring complete data ; competing risks ; Cox model ; subdistribution hazard

Abstract

Competing risks data arise naturally in many biomedical studies. Often, one cause is of primary interest, with the analysis directed primarily at quantifying the effect of risk factors for dying from that cause. The proposed method involves the use of multiple imputation to create "censoring complete" data. Regression methods for the subdistribution hazard model developed by Fine and Gray (1999) are then be applied to the censoring-complete data. Large sample properties are derived and the finite-sample properties are evaluated using simulations. We apply the proposed methods to national kidney transplantation data obtained from the Scientific Registry of Transplant Recipients (SRTR).