4. Bayesian Model Comparison and Model Checking

  1. Xin-Yuan Song and
  2. Sik-Yum Lee

Published Online: 18 JUL 2012

DOI: 10.1002/9781118358887.ch4

Basic and Advanced Bayesian Structural Equation Modeling: With Applications in the Medical and Behavioral Sciences

Basic and Advanced Bayesian Structural Equation Modeling: With Applications in the Medical and Behavioral Sciences

How to Cite

Song, X.-Y. and Lee, S.-Y. (2012) Bayesian Model Comparison and Model Checking, in Basic and Advanced Bayesian Structural Equation Modeling: With Applications in the Medical and Behavioral Sciences, John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9781118358887.ch4

Author Information

  1. Department of Statistics, The Chinese University of Hong Kong

Publication History

  1. Published Online: 18 JUL 2012
  2. Published Print: 24 AUG 2012

Book Series:

  1. Wiley Series in Probability and Statistics

Book Series Editors:

  1. Walter A. Shewhart and
  2. Samuel S. Wilks

ISBN Information

Print ISBN: 9780470669525

Online ISBN: 9781118358887

SEARCH

Keywords:

  • Akaike information criterion (AIC);
  • Bayesian information criterion (BIC);
  • deviance information criterion (DIC);
  • fixed covariates;
  • model checking;
  • path sampling;
  • WinBUGS

Summary

This chapter introduces various Bayesian statistics for hypothesis testing and model comparison and provides some statistical methods for assessment of the goodness of fit of the posited model and for model diagnosis. In Bayesian approach, the chapter considers the issue of hypothesis testing as model comparison, mainly because a hypothesis can be represented via a specific model. In addition to the Bayes factor, the chapter introduces several other Bayesian statistics for model comparison, namely the Bayesian information criterion (BIC), Akaike information criterion (AIC), deviance information criterion (DIC), and the Lv-measure, a criterion-based statistic. The chapter includes discussions related to path sampling and WinBUGS for computing this statistic and provides an application of the methodology to SEMs with fixed covariates. It gives some other methods for model comparison with an illustrative example. The chapter discusses methods for model checking and goodness of fit.

Controlled Vocabulary Terms

Akaike information criterion; Bayesian information criterion; covariate; deviance information criterion; sampling; WinBUGS