|
Activity Number:
|
25
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305520 |
|
Title:
|
The Multivariate Linear Path Model Embedded in the Multiple Indicator and Multiple Causes Model
|
|
Author(s):
|
Youngju Pak*+ and Randly L. Carter
|
|
Companies:
|
University of Missouri-Columbia and State University of New York at Buffalo
|
|
Address:
|
, , MO, 65203,
|
|
Keywords:
|
Path models ; Multivariate methods ; MIMIC models ; latent variables ; Cardiometabolic risk factors ; Diabetes
|
|
Abstract:
|
Multivariate path models can be used to estimate and test direct and indirect effect of a set of endogenous variables on subsequent sets of variables with the assumption of partial causal ordering among endogenous variables. However, often our research question involves investigating direct and indirect effect of a latent variable in the multivariate path model. This lead into the Multivariate Linear Path Model (MLPM) embedded in the Multiple Indicator and Multiple Causes (MIMIC) Model. In this paper, general methodology for inferences for the proposed model is presented. The methods are applied to data from the Western New York Health Study to describe how insulin resistance level plays a role as a link between sets of health behavioral variables and cardiometabolic risk factors.
|
- 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 2009 program |
