Activity Number:
|
288
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 14, 2002 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Biometrics Section*
|
Abstract - #301231 |
Title:
|
Multistate Survival Analysis: A Class of Non and Semiparametric Markov Regression Models Based on Additive Risk
|
Author(s):
|
Youyi Shu*+ and John Klein
|
Affiliation(s):
|
Merck Research Laboratories and Medical College of Wisconsin
|
Address:
|
10 Sentry Parkway, Blue Bell, Pennsylvania, 19422, USA
|
Keywords:
|
multistate survival analysis ; Markov regression models ; multistate models ; Markov models ; additive risk model ; additive hazards model
|
Abstract:
|
When there are covariate effects to be considered, multistate survival analysis is dominated either by parametric Markov regression models or by semi-parametric Markov regression models using Cox's (1972) proportional hazards model to model transition intensities between the states. The purpose of this research work is to study alternatives to Cox's model in a general finite-state Markov model setting. We shall look at two alternative models: Aalen's (1989) nonparametric additive risk model and Lin and Ying's (1994) semi-parametric additive risk model. The former allows the effects of covariates to vary freely over time, while the latter assumes the regression coefficients are constant over time. With basic tools of the product integral and the functional delta-method, we present an estimator of the transition probability matrix and develop the large sample theory for the estimator under each of these two models. Data on 1459 HLA identical sibling transplants for acute leukemia from the International Bone Marrow Transplant Registry serve as illustration.
|