American Statistical Association
New York City
Metropolitan Area Chapter

New York State Psychiatric Institute
at Columbia University Medical Center
Biostatistics Seminar



NONLINEAR STRUCTURAL EQUATION MODELING
AS A STATISTICAL METHOD

by

Melanie Wall, Ph.D.
Associate Professor, Division of Biostatistics,
School of Public Health, University of Minnesota


Abstract

Structural equation analysis allows exploring and modeling relationships among latent variables. The most traditional analysis deals only with linear relationships. However, in applied problems, relevant research questions can be associated with some form of nonlinear relations. Also, from a statistical modeling or data analysis point of view, capabilities to address unrestricted nonlinear relations would be welcome. A review is given of the existing approaches that were developed and designed for specific nonlinear structural equation models. Then, a statistical formulation of general nonlinear structural equation analysis is introduced, and a general model fitting procedure applicable under weak assumptions on latent variable distributions is developed. An example with a non-polynomial nonlinear structural model is discussed using the new method.

Biographical Note

Dr. Melanie Wall is currently Associate Professor in the Division of Biostatistics within the School of Public Health at the University of Minnesota. Her research interests are in statistical methods for latent variable modeling and extending traditional latent variable models (e.g. to include nonlinearities, spatial and longitudinal structure, and both continuous and categorical latent variables) making them more attractive to a variety of researchers. In particular, she works on applying latent variable models to answer research questions relevant for psychosocial and behavioral public health. Dr. Wall developed and has taught an advanced research level course in Latent Variable Measurement Models and Path Analysis over the last eight years to MS and PhD students from diverse departments across the University of Minnesota including public health, psychology, clinical psychology, education, nursing, business administration, and operations research. Finally, Dr. Wall is a current member of the NIH study section for biostatistical methods research and design and is an associate editor for The American Statistician.


Date: Friday, March 13, 2009
Time: 11:00 A.M.
Location: Mailman School of Public Health
Department of Biostatistics
722 West 168th Street
Biostatistics Computer Lab
6th Floor - Room 656
New York, New York

RESERVATIONS ARE NOT REQUIRED

Coffee will be served.


Home Page | Chapter News | Chapter Officers | Chapter Events
Other Metro Area Events | ASA National Home Page | Links To Other Websites
NYC ASA Chapter Constitution | NYC ASA Chapter By-Laws

Copyright © 2009 by New York City Metropolitan Area Chapter of the ASA
Designed and maintained by Cynthia Scherer
Send questions or comments to nycasa@mindspring.com