Extending JAGS: A tutorial on adding custom distributions to JAGS (with a diffusion model example)

We demonstrate how to add a custom distribution into the general-purpose, open-source, cross-platform graphical modeling package JAGS (“Just Another Gibbs Sampler”). JAGS is intended to be modular and extensible, and modules written in the way laid out here can be loaded at runtime as needed and do...

Full description

Saved in:
Bibliographic Details
Published in:Behavior research methods 2014-03, Vol.46 (1), p.15-28
Main Authors: Wabersich, Dominik, Vandekerckhove, Joachim
Format: Article
Language:English
Subjects:
Bayes Theorem
Bayesian analysis
Behavioral Science and Psychology
C plus plus
Cognitive Psychology
Computer Graphics
Diffusion
Diffusion models
Independent sample
Markov analysis
Markov Chains
Models, Psychological
Models, Statistical
Programming Languages
Psychology
Software
Software Design
Software packages
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We demonstrate how to add a custom distribution into the general-purpose, open-source, cross-platform graphical modeling package JAGS (“Just Another Gibbs Sampler”). JAGS is intended to be modular and extensible, and modules written in the way laid out here can be loaded at runtime as needed and do not interfere with regular JAGS functionality when not loaded. Writing custom extensions requires knowledge of C++, but installing a new module can be highly automatic, depending on the operating system. As a basic example, we implement a Bernoulli distribution in JAGS. We further present our implementation of the Wiener diffusion first-passage time distribution, which is freely available at https://sourceforge.net/projects/jags-wiener/ .
ISSN:1554-3528
1554-351X
1554-3528
DOI:10.3758/s13428-013-0369-3