|
Activity Number:
|
468
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309080 |
|
Title:
|
Semiparametric Marginalized Model for Longitudinal Data with a Terminating Event
|
|
Author(s):
|
Mengling Liu*+ and Wenbin Lu
|
|
Companies:
|
New York University and North Carolina State University
|
|
Address:
|
650 First Ave, New York, NY, 10016,
|
|
Keywords:
|
Generalised estimating equations ; Generalised linear model ; Marginalised random-effects model ; Nonignorable dropout ; Transformation model
|
|
Abstract:
|
We investigate marginal inference of longitudinal data when there exists a dependent terminating event. The proposed marginalized model directly specifies marginal associations between longitudinal responses and covariates and incorporates the dependent terminating event, which marginally follows a semiparametric transformation model, through a flexible conditional mean model. We develop an estimation procedure based on a series of asymptotically unbiased estimating equations. The resulting regression estimators are shown to be consistent and asymptotically normal, with a sandwich-type variance-covariance matrix that can be consistently estimated by the usual plug-in rule. The proposed approach is evaluated by simulations under practical settings and illustrated by real data applications.
|
