Jump to ContentJump to Main Navigation
Bayesian ModelsA Statistical Primer for Ecologists$
Users without a subscription are not able to see the full content.

N. Thompson Hobbs and Mevin B. Hooten

Print publication date: 2015

Print ISBN-13: 9780691159287

Published to Princeton Scholarship Online: October 2017

DOI: 10.23943/princeton/9780691159287.001.0001

Show Summary Details
Page of

PRINTED FROM PRINCETON SCHOLARSHIP ONLINE (www.princeton.universitypressscholarship.com). (c) Copyright Princeton University Press, 2022. All Rights Reserved. An individual user may print out a PDF of a single chapter of a monograph in PRSO for personal use.date: 16 May 2022

Inference from Multiple Models

Inference from Multiple Models

(p.209) 9 Inference from Multiple Models
Bayesian Models

N. Thompson Hobbs

Mevin B. Hooten

Princeton University Press

This chapter describes how to evaluate alternative models with data. There are two broad ways to formally use multiple models: model selection and model averaging. In model selection, models are evaluated based on some criterion. In model averaging, inferences are made using all models in the set, or a subset of them, using a weighted average of posterior distributions of individual models. This chapter first discusses model selection before turning to model averaging in turn, before detailing some general considerations which might help the researcher's selection of a particular model, given that both methods have their own strengths and shortcomings.

Keywords:   alternative models, multiple models, model selection, model averaging, posterior distributions, model probabilities

Princeton Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.

Please, subscribe or login to access full text content.

If you think you should have access to this title, please contact your librarian.

To troubleshoot, please check our FAQs , and if you can't find the answer there, please contact us.