|
Activity Number:
|
498
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 7, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
WNAR
|
| Abstract - #300279 |
|
Title:
|
Partial Consistency in Mixed Models
|
|
Author(s):
|
Tao Huang*+ and Heng Peng
|
|
Companies:
|
University of Virginia and Hong Kong Baptist University
|
|
Address:
|
Department of Statistics, Charlottesville, VA, 22904,
|
|
Keywords:
|
Partial Consistency ; Mixed Models ; Correlated Data
|
|
Abstract:
|
The concept of partial consistency is extended to mixed models in the analysis of correlated data. A two-step method is proposed to estimate the random and fixed effects. Comparing to classical estimation methods, the proposed two-step estimation method relaxes assumptions on random effects and alleviates the complexity of computation. The asymptotic properties, especially the efficiency and robustness, of the proposed two-step method will be addressed, and the applicability and effectiveness of the proposed two-step method will be illustrated through simulation studies and real data analyses.
|
