The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
40
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, July 29, 2012 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Bayesian Statistical Science
|
Abstract - #306545 |
Title:
|
Joint Modeling of Binomial and Rank Responses
|
Author(s):
|
Bradley Barney*+ and Federica Amici and Josep Call and Filippo Aureli and Valen E Johnson
|
Companies:
|
Kennesaw State University and Max Planck Institute for Evolutionary Anthropology and Max Planck Institute for Evolutionary Anthropology and Liverpool John Moores University and MD Anderson Cancer Center
|
Address:
|
118 Woodberry Ct, Woodstock, GA, 30188, United States
|
Keywords:
|
Latent Variable ;
Bayesian ;
Intelligence ;
Discrepancy Measure
|
Abstract:
|
Many methods exist for analyzing a collection of binomial responses, and various methods exist for analyzing rank responses. In order to achieve a parsimonious inference when data of both types have been collected, it is critical to jointly model both response types. We present techniques for joint modeling of binomial and rank response data using the Bayesian paradigm for inference. The motivating application consists of results from a series of assessments on several primate species. Among 17 assessments assigned to 4 domains, 3 are considered to have a rank response and the remaining 14 are considered to have a binomial response. In order to model binomial and rank outcomes simultaneously, we adopt the popular technique of data augmentation with latent variables. We also specify how candidate random effect models for the latent variables may be parsimoniously constructed to allow a simple and consistent prior specification for models with differing numbers of random effects. We compare various random effect models using discrepancy measures. In addition to presenting the methodology, we illustrate its application to primate intelligence data.
|
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 2012 program
|
2012 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.