|
Activity Number:
|
380
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305544 |
|
Title:
|
Three-Level Mixed Model with Heterogeneous Within-Subject Variances
|
|
Author(s):
|
Sharada Modur*+ and Elizabeth Stasny and Christopher Hans
|
|
Companies:
|
The Ohio State University and The Ohio State University and The Ohio State University
|
|
Address:
|
1958 Neil Avenue, Columbus, OH, 43210,
|
|
Keywords:
|
Longitudinal Data ; Mixed Model ; Multilevel Models ; MCEM
|
|
Abstract:
|
There is a growing interest in using longitudinal studies to track weight gain as a method of identifying individuals at risk for childhood obesity. One such study, the National Longitudinal Survey of Youth 79 (NLSY79), includes a random sample of women with biometric information on their biological children collected biennially. To estimate child-specific weight trajectories and address the nested structure of the data set, we propose a three-level mixed model. We fit a mixed model for the mean and covariance structure to account for the natural heterogeneity among subjects. We then extend this model to address any remaining heterogeneity in the within-child variances using a regression equation approach. We use the Expectation-Maximization algorithm with a Newton Raphson update. The random effects and within-child variance parameters are treated as "missing data."
|
