Abstract Details
Activity Number:
|
86
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 3, 2014 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Statistics and the Environment
|
Abstract #312714
|
View Presentation
|
Title:
|
A Nonlinear Latent Variable Model for Repeated Follow-Up Data on Methylmercury Neurotoxicity
|
Author(s):
|
Esben Budtz-Jørgensen*+
|
Companies:
|
University of Copenhagen
|
Keywords:
|
latent variable ;
structural equation ;
non-linear
|
Abstract:
|
Standard statistical procedures (such as mixed models) are poorly suited for analysis multivariate longitudinal data may lead to biased and inefficient estimation of the exposure-associated effects. We explore different structural equation models where, multivariate endpoints are considered to be manifestations of causally related latent variables. This structure may provide a parsimonious and more powerful representation of the exposure effect while properly accounting for measurement errors and the complex correlation structure typically encountered in such data. The standard model assumes that latent variables are linearly related. We consider different models relaxing this assumption and illustrate the methods using data from a prospective cohort study linking prenatal mercury exposure to multivariate cognitive test-scores collected at age 7, 14 and 22.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.