|
Activity Number:
|
142
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #301700 |
|
Title:
|
Rasch and Mixture of Generalized Linear Mixed Models for Analysis of Aphasic Deficits of Syntactic Comprehension
|
|
Author(s):
|
Roee Gutman*+ and Gayle DeDe and David Caplan and Jun S. Liu
|
|
Companies:
|
Harvard University and Boston University and Massachusetts General Hospital and Harvard University
|
|
Address:
|
Science Center, Statistics Department, Cambridge, MA, 02138-2901,
|
|
Keywords:
|
Rasch Model ; Mixture models ; Generalized Linear Mixed Models ; Bayesian Analysis
|
|
Abstract:
|
Aphasia is a loss of the ability to produce and/or comprehend language, due to injury to brain areas responsible for these functions. Performance of aphasic patients in comprehension tests is traditionally related to personal ability and to questions' difficulty. Thus, the Rasch model should be adequate to analyze these tests. We modeled the way aphasic patients process sentence types, and their ability to accomplish tasks using Rasch model and Rasch model that incorporates task and sentence grouping effect. These models were examined using psychologically meaningful statistics and were found to be inadequate. We propose a mixture of generalized linear mixed models that cluster patients into similar response patterns and abilities. The mixture model better describes the experimental results of the performance of aphasic patients, and still incorporates the essence of the Rasch model.
|
