Mixtures of g-priors in generalized linear models
From MaRDI portal
Mixtures of \(g\)-priors in generalized linear models
Abstract: Mixtures of Zellner's g-priors have been studied extensively in linear models and have been shown to have numerous desirable properties for Bayesian variable selection and model averaging. Several extensions of g-priors to Generalized Linear Models (GLMs) have been proposed in the literature; however, the choice of prior distribution of g and resulting properties for inference have received considerably less attention. In this paper, we unify mixtures of g-priors in GLMs by assigning the truncated Compound Confluent Hypergeometric (tCCH) distribution to 1/(1 + g), which encompasses as special cases several mixtures of g-priors in the literature, such as the hyper-g, Beta-prime, truncated Gamma, incomplete inverse-Gamma, benchmark, robust, hyper-g/n, and intrinsic priors. Through an integrated Laplace approximation, the posterior distribution of 1/(1 + g) is in turn a tCCH distribution, and approximate marginal likelihoods are thus available analytically, leading to "Compound Hypergeometric Information Criteria" for model selection. We discuss the local geometric properties of the g-prior in GLMs and show how the desiderata for model selection proposed by Bayarri et al, such as asymptotic model selection consistency, intrinsic consistency, and measurement invariance may be used to justify the prior and specific choices of the hyper parameters. We illustrate inference using these priors and contrast them to other approaches via simulation and real data examples. The methodology is implemented in the R package BAS and freely available on CRAN.
Recommendations
- Mixtures of g Priors for Bayesian Variable Selection
- Hyper-\(g\) priors for generalized linear models
- Mixtures of \(g\)-priors for Bayesian model averaging with economic applications
- A mixture of g-priors for variable selection when the number of regressors grows with the sample size
- scientific article; zbMATH DE number 1983940
Cites work
- A comment on D. V. Lindley's statistical paradox
- A New Perspective on Priors for Generalized Linear Models
- A Reference Bayesian Test for Nested Hypotheses and its Relationship to the Schwarz Criterion
- Accurate Approximations for Posterior Moments and Marginal Densities
- An Intrinsic Limiting Procedure for Model Selection and Hypotheses Testing
- Approximate Bayes factors and accounting for model uncertainty in generalised linear models
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Approximate Bayesian model selection with the deviance statistic
- Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information
- Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem
- Bayes Factors
- Bayes Factors Based on Test Statistics
- Bayesian model selection using test statistics
- Bayesian variable selection using cost-adjusted BIC, with application to cost-effective measurement of quality of health care
- Benchmark priors for Bayesian model averaging.
- Calibration and empirical Bayes variable selection
- Clinical prediction models. A practical approach to development, validation, and updating.
- Computation for intrinsic variable selection in normal regression models via expected-posterior prior
- Computationally convenient distributional assumptions for common-value auctions
- Consistency of hyper-\(g\)-prior-based Bayesian variable selection for generalized linear models
- Criteria for Bayesian model choice with application to variable selection
- Double Exponential Families and Their Use in Generalized Linear Regression
- Empirical Bayes vs. fully Bayes variable selection
- Forecast combination and Bayesian model averaging: a prior sensitivity analysis
- Fully Bayes factors with a generalized g-prior
- Fully Exponential Laplace Approximations to Expectations and Variances of Nonpositive Functions
- scientific article; zbMATH DE number 3844851 (Why is no real title available?)
- scientific article; zbMATH DE number 5133222 (Why is no real title available?)
- scientific article; zbMATH DE number 5629278 (Why is no real title available?)
- scientific article; zbMATH DE number 4070082 (Why is no real title available?)
- scientific article; zbMATH DE number 4098511 (Why is no real title available?)
- scientific article; zbMATH DE number 3716572 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- scientific article; zbMATH DE number 409719 (Why is no real title available?)
- scientific article; zbMATH DE number 1932867 (Why is no real title available?)
- scientific article; zbMATH DE number 3998953 (Why is no real title available?)
- scientific article; zbMATH DE number 1432028 (Why is no real title available?)
- scientific article; zbMATH DE number 5224911 (Why is no real title available?)
- scientific article; zbMATH DE number 3249515 (Why is no real title available?)
- scientific article; zbMATH DE number 3189754 (Why is no real title available?)
- Hyper-\(g\) priors for generalized linear models
- Inference from intrinsic Bayes' procedures under model selection and uncertainty
- Informative \(g\)-priors for logistic regression
- Mixtures of g Priors for Bayesian Variable Selection
- Mixtures of \(g\)-priors for Bayesian model averaging with economic applications
- Model Selection and the Principle of Minimum Description Length
- Objective Bayesian Variable Selection
- On Sampling Strategies in Bayesian Variable Selection Problems With Large Model Spaces
- On the computational complexity of high-dimensional Bayesian variable selection
- On the existence of maximum likelihood estimates in logistic regression models
- On the use of Cauchy prior distributions for Bayesian logistic regression
- Plane Answers to Complex Questions
- Power-expected-posterior priors for generalized linear models
- Properties of Bayes Factors Based on Test Statistics
- Regularization in regression: comparing Bayesian and frequentist methods in a poorly informative situation
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- The Intrinsic Bayes Factor for Model Selection and Prediction
- The risk inflation criterion for multiple regression
Cited in
(30)- A mixture of g-priors for variable selection when the number of regressors grows with the sample size
- An adaptive MCMC method for Bayesian variable selection in logistic and accelerated failure time regression models
- A model selection approach for variable selection with censored data
- Predicting competitions by combining conditional logistic regression and subjective Bayes: an Academy Awards case study
- Multi-scale shotgun stochastic search for large spatial datasets
- The generalized log-gamma mixture model with covariates: local influence and residual analysis
- Hyper-\(g\) priors for generalized linear models
- A review of Brown 1971 (in)admissibility results under scale mixtures of Gaussian priors
- Mixtures of g Priors for Bayesian Variable Selection
- A study of variable selection using \(g\)-prior distribution with ridge parameter
- Catalytic prior distributions with application to generalized linear models
- Bayesian Model Selection in Additive Partial Linear Models Via Locally Adaptive Splines
- Mixtures of \(g\)-priors for Bayesian model averaging with economic applications
- A conditional Lindley paradox in Bayesian linear models
- Heterogeneous data analysis using a mixture of Laplace models with conjugate priors
- Extremely randomized neural networks for constructing prediction intervals
- Model Uncertainty Quantification in Cox Regression
- Classified generalized linear mixed model prediction incorporating pseudo‐prior information
- Bayesian Calibration of p‐Values from Fisher's Exact Test
- Power-expected-posterior priors as mixtures of \(g\)-priors in normal linear models
- A note on consistency of Bayesian high-dimensional variable selection under a default prior
- Empirical Bayes methods in variable selection
- A tractable Bayesian joint model for longitudinal and survival data
- Bayes oracle property of multiple tests of multivariate normal means under sparsity
- Bayesian adaptive variable selection with a generalized g-prior
- Laplace power-expected-posterior priors for logistic regression
- Bayesian hierarchical models with calibrated mixtures of g-priors for assessing treatment effect moderation in meta-analysis
- Model selection-based estimation for generalized additive models using mixtures of g-priors: towards systematization
- Testing high-dimensional regression coefficients in linear models via Bayes factor
- Informative \(g\)-priors for logistic regression
This page was built for publication: Mixtures of \(g\)-priors in generalized linear models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3121572)
