|
Activity Number:
|
378
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #306762 |
|
Title:
|
Alternative Structural Models for Analyzing Multivariate Longitudinal Data
|
|
Author(s):
|
Feng Gao*+ and Paul Thompson and Chengjie Xiong and J. Philip Miller
|
|
Companies:
|
Washington University School of Medicine and Washington University School of Medicine and Washington University School of Medicine and Washington University School of Medicine
|
|
Address:
|
660 S. Euclid Ave., St Louis, 63021,
|
|
Keywords:
|
multivariate longitudinal data ; structural equation modeling ; cross-lagged regression model ; latent growth curve model
|
|
Abstract:
|
Multivariate longitudinal data provides a unique opportunity in studying the joint evolution of multiple response variables over time. However, the analysis of multivariate longitudinal data can be challenging because the errors are likely to be correlated for the same marker measured at different occasions and the errors are also likely to be correlated among markers measured at the same time. Structural equation modeling (SEM) is a comprehensive statistical approach to identify patterns of directional and non-directional relationships among a set of variables. In this talk, with application to a real-world study to evaluate the joint evolution of the biomarkers for renal structure and function, 3 alternative SEMs are presented and compared: a) a cross-lagged regression model, b) a latent growth curve model and c) a dynamic model based on latent difference scores.
|
