A Sequential Monte Carlo Algorithm to Incorporate Model Uncertainty in Bayesian Sequential Design

This article presents a sequential Monte Carlo (SMC) algorithm that can be used for any one-at-a-time Bayesian sequential design problem in the presence of model uncertainty where discrete data are encountered. Our focus is on adaptive design for model discrimination but the methodology is applicabl...

Full description

Saved in:
Bibliographic Details
Published in:Journal of computational and graphical statistics 2014-03, Vol.23 (1), p.3-24
Main Authors: Drovandi, Christopher C., McGree, James M., Pettitt, Anthony N.
Format: Article
Language:English
Subjects:
Algorithms
Bayesian Methodology
Design optimization
Dose response relationship
Entropy
Estimation methods
Experiment design
Information industry
Information theory
Model discrimination
Monte Carlo simulation
Mutual information
Optimal design
Parameter estimation
Particle filter
Probabilities
Studies
Utility functions
Utility models
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:This article presents a sequential Monte Carlo (SMC) algorithm that can be used for any one-at-a-time Bayesian sequential design problem in the presence of model uncertainty where discrete data are encountered. Our focus is on adaptive design for model discrimination but the methodology is applicable if one has a different design objective such as parameter estimation or prediction. An SMC algorithm is run in parallel for each model and the algorithm relies on a convenient estimator of the evidence of each model that is essentially a function of importance sampling weights. Methods that rely on quadrature for this task suffer from the curse of dimensionality. Approximating posterior model probabilities in this way allows us to use model discrimination utility functions derived from information theory that were previously difficult to compute except for conjugate models. A major benefit of the algorithm is that it requires very little problem-specific tuning. We demonstrate the methodology on three applications, including discriminating between models for decline in motor neuron numbers in patients suffering from motor neuron disease. Computer code to run one of the examples is provided as online supplementary materials.
ISSN:1061-8600
1537-2715
DOI:10.1080/10618600.2012.730083