|
Activity Number:
|
195
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #300843 |
|
Title:
|
Extension of Flowgraph Models with Covariates for Evaluating Effects of Kidney Retransplantation
|
|
Author(s):
|
Ya-Hui Hsueh*+ and C. Lillian Yau
|
|
Companies:
|
Tulane University School of Public Health and Tropical Medicine and Tulane University School of Public Health and Tropical Medicine
|
|
Address:
|
1440 Canal St. Suite 2001, New Orleans, LA, 70112,
|
|
Keywords:
|
Saddlepoint Approximation ; Survival Analysis ; time-to-event data ; Flowgraph model ; semi-Markov models
|
|
Abstract:
|
Flowgraph models offer a useful data analytical tool for multistate models, and have been applied effectively in modeling censored and incomplete survival data. Recently, it has been shown that flowgraph model can also serve as a regression technique to assess the effects of covariates under the Bayesian framework. We further the development of detecting the effects of covariates by maximizing the likelihood function of the flowgraph model. Hypothesis testings for estimated parameters of covariates in a flowgraph model are proposed. Kidney transplant data from United Network for Organ Sharing (UNOS) Organization Registry is used to illustrate the extension of flowgraph models. The proposed model will enhance the ability for evaluating the effects of kidney retransplantation.
|
