Objective Bayesian comparison of constrained analysis of variance models

DOI10.1007/S11336-016-9516-YzbMATH Open1402.62040arXiv1405.4801OpenAlexW1651663237WikidataQ39322044 ScholiaQ39322044MaRDI QIDQ1682437FDOQ1682437

Authors: Guido Consonni, R. Paroli 

Publication date: 30 November 2017

Published in: Psychometrika (Search for Journal in Brave)

Abstract: In the social sciences we are often interested in comparing models specified by parametric equality or inequality constraints. For instance, when examining three group means $m{u}_1,m{u}_2,m{u}_3$ through an analysis of variance (ANOVA), a model may specify that $m{u}_1<m{u}_2<m{u}_3$, while another one may state that $m{u}_1=m{u}_3<m{u}_2$, and finally a third model may instead suggest that all means are unrestricted. This is a challenging problem, because it involves a combination of non-nested models, as well as nested models having the same dimension. We adopt an objective Bayesian approach, and derive the posterior probability of each model under consideration. Our method is based on the intrinsic prior methodology, with suitably modifications to accommodate equality and inequality constraints. Focussing on normal ANOVA models, a comparative assessment is carried out through simulation studies, showing that correct model identification is possible even in situations where frequentist power is low. We also present an application to real data collected in a psychological experiment.

Full work available at URL: https://arxiv.org/abs/1405.4801

Recommendations

• Objective Bayesian model selection approach to the two way analysis of variance
• Objective Bayesian multiple comparisons for normal variances
• Objective Bayesian comparison of order-constrained models in contingency tables
• Bayesian comparison of models with inequality and equality constraints
• Comparison of Bayesian objective procedures for variable selection in linear regression
• Bayesian semiparametric analysis and model comparison for confirmatory factor model
• Analysis of variance for Bayesian inference

zbMATH Keywords

ANOVAhypothesis testingBayes factorBayesian model choiceinequality constraintintrinsic prior

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Bayesian inference (62F15) Analysis of variance and covariance (ANOVA) (62J10) Applications of statistics to psychology (62P15)

Cites Work

• Bayes factors for testing order-constrained hypotheses on correlations
• An encompassing prior generalization of the Savage-Dickey density ratio
• Bayesian model selection of informative hypotheses for repeated measurements
• Marginal Likelihood from the Gibbs Output
• Constrained Statistical Inference
• Mixtures of g Priors for Bayesian Variable Selection
• Title not available (Why is that?)
• Bayes Factors
• Calibration of \(\rho \) values for testing precise null hypotheses
• Title not available (Why is that?)
• Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem
• Using MCMC chain outputs to efficiently estimate Bayes factors
• The Bayes factor for inequality and about equality constrained models
• Prior adjusted default Bayes factors for testing (in)equality constrained hypotheses
• Equality and inequality constrained multivariate linear models: objective model selection using constrained posterior priors
• The Intrinsic Bayes Factor for Model Selection and Prediction
• Title not available (Why is that?)
• Default Bayes Factors for Nonnested Hypothesis Testing
• Bayes factors for testing inequality constrained hypotheses: issues with prior specification
• Marginal Likelihood From the Metropolis–Hastings Output
• Bayesian methods for the analysis of inequality constrained contingency tables
• Consistency of objective Bayes factors as the model dimension grows
• Title not available (Why is that?)
• Title not available (Why is that?)
• Consistency of Bayesian procedures for variable selection
• Title not available (Why is that?)
• Objective Testing Procedures in Linear Models: Calibration of the p‐values
• Objective Bayesian Variable Selection
• The case for objective Bayesian analysis
• Objective Bayesian model selection in Gaussian graphical models
• Expected-posterior prior distributions for model selection
• Title not available (Why is that?)
• Compatibility of prior specifications across linear models
• Revised standards for statistical evidence
• Bayesian evaluation of informative hypotheses
• Assessing robustness of intrinsic tests of independence in two-way contingency tables
• Hypothesis assessment and inequalities for Bayes factors and relative belief ratios
• Title not available (Why is that?)
• Objective Bayesian search of Gaussian directed acyclic graphical models for ordered variables with non-local priors
• Objective Bayesian methods for one-sided testing
• Tests based on intrinsic priors for the equality of two correlated proportions
• Objective Bayes factors for inequality constrained hypotheses
• Bayesian inference through encompassing priors and importance sampling for a class of marginal models for categorical data
• Choosing priors for constrained analysis of variance: methods based on training data

Cited In (7)

• Bayes factor testing of multiple intraclass correlations
• The whetstone and the alum block: balanced objective Bayesian comparison of nested models for discrete data
• Prior distributions for objective Bayesian analysis
• Bayesian comparison of models with inequality and equality constraints
• Objective Bayesian model discrimination in follow-up experimental designs
• Objective Bayesian comparison of order-constrained models in contingency tables
• Choosing priors for constrained analysis of variance: methods based on training data

Uses Software

• BOCOR

This page was built for publication: Objective Bayesian comparison of constrained analysis of variance models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1682437)