JSM 2014 Home
Online Program Home
My Program

Abstract Details

Activity Number: 70
Type: Contributed
Date/Time: Sunday, August 3, 2014 : 4:00 PM to 5:50 PM
Sponsor: Biometrics Section
Abstract #312878 View Presentation
Title: Bivariate Interaction Models in the Context of Generalized Linear Mixed Models
Author(s): Karen Nielsen*+ and Richard Gonzalez
Companies: University of Michigan and University of Michigan
Keywords: interaction ; GLMM ; visualization
Abstract:

When exploring data with possible interactions between predictor variables, researchers often artificially dichotomize or split one continuous variable. This allows for simple two-dimensional plots and tests of slope for specified levels of the predictors, but it oversimplifies the situation. Some work has already been done on probing the simple interaction between two continuous variables (e.g., Bauer and Curran, 2005), but even that may not be enough to capture the complex relationship that might exist between predictors. We propose a bivariate 2nd-order interaction model in the context of the generalized linear mixed model for exploring the interaction between variables and the resulting effects on the response. This approach also allows a different testing method by focusing on an underlying basis set for each variable - polynomial or otherwise. We will discuss the interpretation advantages this may yield as well as the importance of using informative visualizations to guide inference.


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.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.