A weakly informative default prior distribution for logistic and other regression models

DOI10.1214/08-AOAS191zbMath1156.62017arXiv0901.4011WikidataQ112778344 ScholiaQ112778344MaRDI QIDQ999667

Andrew Gelman, Aleks Jakulin, Yu-Sung Su, Maria Grazia Pittau

Publication date: 10 February 2009

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0901.4011

zbMATH Keywords

least squares; logistic regression; hierarchical model; linear regression; Bayesian inference; generalized linear model; noninformative prior distribution; multilevel model; weakly informative prior distribution

Mathematics Subject Classification ID

62F15: Bayesian inference

62J12: Generalized linear models (logistic models)

Related Items

Comment on article by Rubio and Steel, Estimating treatment effect heterogeneity in randomized program evaluation, Multivariate Bayesian logistic regression for analysis of clinical study safety issues, Bayesian nonparametric weighted sampling inference, Bayesian latent pattern mixture models for handling attrition in panel studies with refreshment samples, An objective Bayesian estimation of parameters in a log-binomial model, Probability aggregation in time-series: dynamic hierarchical modeling of sparse expert beliefs, A note on Bayesian robustness for count data, Bayesian model selection for logistic regression models with random intercept, Weak informativity and the information in one prior relative to another, A limit result for the prior predictive applied to checking for prior-data conflict, The predictive Lasso, Informative \(g\)-priors for logistic regression, Bayes, Jeffreys, prior distributions and the philosophy of statistics, On a generalization of the Laplace approximation, Adaptive-modal Bayesian nonparametric regression, Neutral noninformative and informative conjugate beta and gamma prior distributions, Rating scales as predictors -- the old question of scale level and some answers, Theory of self-learning \(Q\)-matrix, A nondegenerate penalized likelihood estimator for variance parameters in multilevel models, Bayesian spatiotemporal analysis of zero-inflated biological population density data by a delta-normal spatiotemporal additive model, Bayesian Estimation of the Log–linear Exponential Regression Model with Censorship and Collinearity, Multiple comparisons in genetic association studies: a hierarchical modeling approach, Closed‐population capture–recapture modeling of samples drawn one at a time, Bayesian Semiparametric Multiple Shrinkage

Uses Software

• UCI-ml
• Mcmcpack
• MICE
• BayesDA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bias reduction in exponential family nonlinear models
• Robust Bayes and empirical Bayes analysis with \(\epsilon\)-contaminated priors
• Do robust estimators work with real data?
• Estimation of a covariance matrix using the reference prior
• Putting Background Information About Relative Risks into Conjugate Prior Distributions
• Multiple Imputation After 18+ Years
• On the existence of maximum likelihood estimates in logistic regression models
• Bayesian Selection and Clustering of Polymorphisms in Functionally Related Genes
• Bayesian Methods in Practice: Experiences in the Pharmaceutical Industry
• Approximate Bayes factors and accounting for model uncertainty in generalised linear models
• The Selection of Prior Distributions by Formal Rules
• A New Perspective on Priors for Generalized Linear Models
• Bias reduction of maximum likelihood estimates
• Invariant Prior Distributions