|
Activity Number:
|
143
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
ENAR
|
| Abstract - #302418 |
|
Title:
|
Demonstration of User-Written Software in Stata, R, and Matlab for Analysis of a Familial Correlation Structure in a Quasi-Least Squares Analysis of Weight Loss in the SHARE Study
|
|
Author(s):
|
Xiaoying Wu*+ and Jichun Xie and Sarah Ratcliffe and Shiriki Kumanyika and Justine Shults+
|
|
Companies:
|
University of Pennsylvania and University of Pennsylvania and University of Pennsylvania and University of Pennsylvania and University of Pennsylvania
|
|
Address:
|
501 Blockley Hall, SOM CCEB, Philadelphia, PA, 19104, 610 Blockley Hall, School of Medicine, Philadelphia, PA, 19104-6021,
|
|
Keywords:
|
quasi-least squares ; longitudinal data ; correlation structure ; familial structure ; intervention analysis
|
|
Abstract:
|
The SHARE study was designed to facilitate weight loss in African American men and women. In this presentation I describe a quasi-least squares (QLS) analysis with a familial correlation structure to describe the pattern of association among the repeated measurements on participants in SHARE. Application of the familial structure improves our ability to understand the role that social support plays in weight loss. My is to describe implementation of our user written software in Stata, R, and Matlab for implementation of the familial correlation structure in QLS. I will describe where to obtain our software and how to apply it in analysis of longitudinal data that previously might have been analyzed using generalized estimating equations (GEE) with one of the simpler correlation structures that is available for GEE.
|
- 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 2008 program |
