This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 396
Type: Topic Contributed
Date/Time: Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
Sponsor: Section on Survey Research Methods
Abstract - #306819
Title: Modeling Longitudinal Dyadic Data with Informative Dropout
Author(s): Guangyu Zhang*+ and Ying Yuan
Companies: University of Maryland and MD Anderson Cancer Center
Address: 2234A, SPH , College Park, MD, 20742,
Keywords: missng data ; longitudinal Dyadic data ; mixed-effect hybrid models ; informative dropout
Abstract:

Dyadic data is common in social and behavior science. Members of dyads often influence each, leading to interdependence (or correlation) structure in the responses. A common problem of longitudinal dyadic data is the increasing number of dropouts. In this study we use mixed-effect hybrid models (MEHMs) to study the longitudinal dyadic data with informative dropout. We model repeated measures on the same subject by transition models and the correlation due to the dyadic structure by random effects. To model the missing data mechanism, we assume that the distribution of missingness depends on both the past history of the longitudinal process and the current outcome, but not on future observations. We use data from a breast cancer study to illustrate the models.


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 2010 program




2010 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.