|
Activity Number:
|
132
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #305126 |
|
Title:
|
Individual-Level Residual Diagnostics for Bayesian Structural Equation Models
|
|
Author(s):
|
Abbie Stokes-Riner*+ and Sally W. Thurston
|
|
Companies:
|
University of Rochester and University of Rochester
|
|
Address:
|
, Rochester, NY, ,
|
|
Keywords:
|
diagnostics ; residuals ; Bayesian ; structural equation model ; latent variable
|
|
Abstract:
|
Structural equation models (SEM) can be a useful tool for studying the effects of multiple correlated exposures on a health outcome measured by multiple outcomes. Recently the use of Bayesian methods for estimating the parameters in SEM has increased, but little attention has been given to examining the assumptions required for SEM. We review existing residual diagnostics used for SEM fit using frequentist methods. Then we define Bayesian residuals for SEM along with posterior-predictive p-values for testing the modeling assumptions. The diagnostics are compared in a simulation study and illustrated with an example from environmental epidemiology.
|
- 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 |
