An alternative to the standard Bayesian procedure for discrimination between normal linear models

DOI10.1093/biomet/71.3.575zbMath0562.62028OpenAlexW2037055640WikidataQ63362868 ScholiaQ63362868MaRDI QIDQ3675330

Luís Raúl Pericchi

Publication date: 1984

Published in: Biometrika (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1093/biomet/71.3.575

zbMATH Keywords

sensitivitynormal linear modelsBayesian model discriminationLindley paradoxexpected gains in informationneutral discriminationprior probability models

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15) Bayesian problems; characterization of Bayes procedures (62C10)

Related Items

Some connections between Bayesian and non-Bayesian methods for regression model selection ⋮ On minimizing chi-square distances under the hypothesis of homogeneity or independence for a two-way contingency table ⋮ Objective Bayesian group variable selection for linear model ⋮ Bayesian Model Selection using Test Statistics ⋮ A monte carlo study on minimizing chi-square distances under the hypothesis of homogeneity or independence for a two-way cotingeney table ⋮ Alternative Bayes factors for model selection ⋮ Benchmark priors for Bayesian model averaging. ⋮ Joint specification of model space and parameter space prior distributions ⋮ Comparison of Bayesian objective procedures for variable selection in linear regression ⋮ Objective Bayesian variable selection in linear regression model ⋮ A new method to discriminate between enzyme-kinetic models