JSM 2011 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Abstract Details

Activity Number: 524
Type: Contributed
Date/Time: Wednesday, August 3, 2011 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #303399
Title: Generalized Multiple Indicators, Multiple Causes Measurement Error Models
Author(s): Carmen Dwele Tekwe*+ and Randy L. Carter
Companies: Texas A & M University and University at Buffalo
Address: Department of Statistics, College Station, TX, 77840,
Keywords: Berkson error ; measurement error ; MIMIC models ; non-linear models ; structural equation models ; atomic bomb survivors

Multiple indicators, multiple causes (MIMIC) models are useful for studying the effects of a latent variable on several outcomes, when causes of the explanatory latent variable are observed. Classical measurement error is uncorrelated with the latent variable; while a Berkson error is uncorrelated with its estimate. Previous work has focused on MIMIC models, where the causes of the latent variable are observed without error. We generalize the MIMIC model to allow non-linear relationships and also allow both Berkson error and classical measurement error in the determinants of the causal equation by defining the G-MIMIC ME model. We propose MC-EM based estimation procedures for the G-MIMIC ME models and apply our results to data collected on atomic bomb survivors.

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 2011 program

2011 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.