|
Activity Number:
|
374
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 15, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Health Policy Statistics*
|
| Abstract - #300992 |
|
Title:
|
Regression Modelling of Gap Time Hazard Functions for Serial Failure Time Data
|
|
Author(s):
|
Douglas Schaubel*+ and Jianwen Cai
|
|
Affiliation(s):
|
University of North Carolina, Chapel Hill and University of North Carolina, Chapel Hill
|
|
Address:
|
CB #7420, McGavran-Greenberg Hall, Chapel Hill, North Carolina, 27599-7420, USA
|
|
Keywords:
|
induced dependent censoring ; multivariate survival ; proportional hazards model ; semi-parametric model ; serial events
|
|
Abstract:
|
Multivariate failure time data can be broadly classified into parallel and serial systems, where parallel processes operate concurrently and serial processes operate sequentially. Although total times (i.e., distance from time origin) may be of interest for parallel processes, inter-event (gap) times are usually of interest for serial processes. Generally, even when total times are independently censored, all gap times except the first are subject to induced dependent censoring. We propose estimating equations for fitting proportional hazards regression models to the gap times of a serial failure time process. Model parameters are shown to be consistent and asymptotically normal. Simulation studies reveal the appropriateness of the asymptotic approximations in finite samples. The proposed methods are applied to kidney transplant data to assess the association between demographic covariates and (i) time until wait-listing (ii) time from wait-listing to transplantation.
|
