Activity Number:
|
350
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Nonparametric Statistics*
|
Abstract - #300719 |
Title:
|
A Robust Procedure for Generalized Estimating Equations: Biostatistical Applications
|
Author(s):
|
Diana Cucos*+ and Joseph McKean+ and Ash Abebe
|
Affiliation(s):
|
Western Michigan University and Western Michigan University and Western Michigan University
|
Address:
|
, Kalamazoo, Michigan, 49008, USA , Kalamazoo, Michigan, 49008, USA
|
Keywords:
|
Wilcoxon ; High breakdown ; Nonlinear regression ; Longitudinal data
|
Abstract:
|
This talk presents a robust alternative to the generalized estimating equation (GEE) method. The proposed estimator is rank-based, which is analogous to the least squares approach, except another norm is used in place of the Euclidean norm. It generalizes the Wilcoxon procedures in simple location models. It offers a complete inference: estimation, confidence procedures, and testing. We will briefly present its asymptotic properties, which are established using a weighted nonlinear regression formulation. Besides providing a viable alternative to analyzing continuous longitudinal data, the method is resistant to outliers as shown by a simulation study. The method is then applied to several real biostatistical data sets, including a pediatric pulmonology data set.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2002 program |