The BiP Seminar
Time: 2:00 pm – 3:30 pm
Date: 4th of May 2018
Place: Room 3001.
Quentin F. GRONAU (University of Amsterdam) “Bayesian Model Comparison for Hierarchical Multinomial Processing Tree Models using Warp-III Bridge Sampling “

Abstract:

Multinomial processing trees (MPTs) are substantively motivated stochastic models for the analysis of categorical data. MPTs are popular in various areas of psychology and have been applied, for instance, in research on memory, perception, logical reasoning, and attitudes. MPTs allow researchers to test theories about cognitive architecture by formalizing qualitatively different cognitive processes that underlie performance in an experimental paradigm. In typical applications, researchers compare several MPTs, each equipped with many parameters, especially when the models are implemented in a hierarchical framework. A Bayesian solution is to compute posterior model probabilities and Bayes factors. Both quantities, however, rely on the marginal likelihood, a high-dimensional integral that cannot be evaluated analytically. Here, we demonstrate how Warp-III bridge sampling can be used to compute the marginal likelihood for hierarchical MPTs. We illustrate the procedure with two published data sets.

 
Organizers:
Nicolas CHOPIN – Robin RYDER
Sponsors:
CREST