Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem

DOI10.1214/10-AOS792MaRDI QIDQ605920zbMATH OpenFDO

Authors James G. Scott, James O. Berger

Publication date 15 November 2010

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

Full work available at URL https://arxiv.org/abs/1011.2333

zbMATH Keywords

variable selectionmultiple testingempirical BayesBayesian model selection

Mathematics Subject Classification ID

Bayesian inference (62F15) Linear regression; mixed models (62J05) Empirical decision procedures; empirical Bayes procedures (62C12) Paired and multiple comparisons; multiple testing (62J15)

Abstract: This paper studies the multiplicity-correction effect of standard Bayesian variable-selection priors in linear regression. Our first goal is to clarify when, and how, multiplicity correction happens automatically in Bayesian analysis, and to distinguish this correction from the Bayesian Ockham's-razor effect. Our second goal is to contrast empirical-Bayes and fully Bayesian approaches to variable selection through examples, theoretical results and simulations. Considerable differences between the two approaches are found. In particular, we prove a theorem that characterizes a surprising aymptotic discrepancy between fully Bayes and empirical Bayes. This discrepancy arises from a different source than the failure to account for hyperparameter uncertainty in the empirical-Bayes estimate. Indeed, even at the extreme, when the empirical-Bayes estimate converges asymptotically to the true variable-inclusion probability, the potential for a serious difference remains.

Recommendations

• Empirical Bayes vs. fully Bayes variable selection
• Multivariate Bayesian Variable Selection and Prediction
• Bayesian variable selection
• Bayesian Semiparametric Analysis of Multivariate Continuous Responses, With Variable Selection
• scientific article; zbMATH DE number 1034042
• Compound decision in the presence of proxies
• Empirical Bayes approach to multiparameter estimation: With special reference to multinomial distribution

Cites work

• scientific article; zbMATH DE number 4159874 (Why is no real title available?)
• scientific article; zbMATH DE number 4070082 (Why is no real title available?)
• scientific article; zbMATH DE number 3716572 (Why is no real title available?)
• scientific article; zbMATH DE number 51418 (Why is no real title available?)
• scientific article; zbMATH DE number 3189754 (Why is no real title available?)
• A Bayesian Mixture Model for Differential Gene Expression
• A Bayesian perspective on the Bonferroni adjustment
• A practical affine equivariant multivariate median
• An exploration of aspects of Bayesian multiple testing
• Bayes factors and marginal distributions in invariant situations
• Bayesian Multiple Comparisons Using Dirichlet Process Priors
• Bayesian perspectives on multiple comparisons.
• Calibration and empirical Bayes variable selection
• Empirical Bayes vs. fully Bayes variable selection
• Empirical Bayes: Past, Present and Future
• Mixtures of g Priors for Bayesian Variable Selection
• Needles and straw in haystacks: Empirical Bayes estimates of possibly sparse sequences
• Nonparametric Bayesian multiple testing for longitudinal performance stratification
• Objective Bayesian model selection in Gaussian graphical models
• Optimal predictive model selection.
• Posterior model probabilities via path‐based pairwise priors
• Statistical decision theory and Bayesian analysis. 2nd ed
• Sums of Logarithms of Binomial Coefficients

Cited in

(only showing first 100 items - show all)

• In mixed company: Bayesian inference for bivariate conditional copula models with discrete and continuous outcomes
• Approximate Bayesian model selection with the deviance statistic
• Posterior model consistency in variable selection as the model dimension grows
• Exploring dependence between categorical variables: benefits and limitations of using variable selection within Bayesian clustering in relation to log-linear modelling with interaction terms
• On the role of the prior in multiplicity adjustment
• Power-Expected-Posterior Methodology with Baseline Shrinkage Priors
• Analysis of binary longitudinal data with time-varying effects
• Neuronized Priors for Bayesian Sparse Linear Regression
• Asymptotic theory of dependent Bayesian multiple testing procedures under possible model misspecification
• Non-marginal decisions: a novel Bayesian multiple testing procedure
• Posterior consistency in frailty models and simulation studies to test the presence of random effects
• The quantile probability model
• Bayesian variable selection in a class of mixture models for ordinal data: a comparative study
• Joint Bayesian estimation of voxel activation and inter-regional connectivity in fMRI experiments
• The horseshoe estimator: posterior concentration around nearly black vectors
• Bayesian model selection for analyzing predictor-dependent directional data
• Online Bayesian variable selection and Bayesian model averaging for streaming data
• Mixtures of \(g\)-priors for Bayesian model averaging with economic applications
• A sparse empirical Bayes approach to high-dimensional Gaussian process-based varying coefficient models
• A Bayesian group selection with compositional responses for analysis of radiologic tumor proportions and their genomic determinants
• Variable Selection in the Presence of Factors: A Model Selection Perspective
• On spike and slab empirical Bayes multiple testing
• Asymptotic Bayes-optimality under sparsity of some multiple testing procedures
• Bayesian inference on group differences in multivariate categorical data
• Bayesian L _1/2 Regression
• Accelerated Structured Matrix Factorization
• An empirical Bayes procedure for the selection of Gaussian graphical models
• Criteria for Bayesian model choice with application to variable selection
• On the convenience of heteroscedasticity in highly multivariate disease mapping
• A hybrid deterministic-deterministic approach for high-dimensional Bayesian variable selection with a default prior
• Combining a relaxed EM algorithm with Occam's razor for Bayesian variable selection in high-dimensional regression
• Discovering interactions using covariate informed random partition models
• Sub-optimality of some continuous shrinkage priors
• Bayesian nonparametric variable selection as an exploratory tool for discovering differentially expressed genes
• Bayesian inference on hierarchical nonlocal priors in generalized linear models
• Consistent high-dimensional Bayesian variable selection via penalized credible regions
• Bayesian model selection in high-dimensional settings
• Learning from a lot: empirical Bayes for high-dimensional model-based prediction
• Bayesian \(l_0\)-regularized least squares
• Directed cyclic graphs for simultaneous discovery of time-lagged and instantaneous causality from longitudinal data using instrumental variables
• A loss-based prior for variable selection in linear regression methods
• A Bayesian nonparametric multiple testing procedure for comparing several treatments against a control
• Prior distributions for objective Bayesian analysis
• A new minimal training sample scheme for intrinsic Bayes factors in censored data
• Subjective Bayesian testing using calibrated prior probabilities
• Nearly optimal Bayesian shrinkage for high-dimensional regression
• Bayesian approaches for large biological networks
• Dirichlet-tree multinomial mixtures for clustering microbiome compositions
• Variations of power-expected-posterior priors in normal regression models
• The spike-and-slab LASSO
• Null-free false discovery rate control using decoy permutations
• Operationalizing Legislative Bodies: A Methodological and Empirical Perspective with a Bayesian Approach
• Skinny Gibbs: a consistent and scalable Gibbs sampler for model selection
• Scalable approximate MCMC algorithms for the horseshoe prior
• Bayesian variable selection for latent class models
• Functional clustering methods for binary longitudinal data with temporal heterogeneity
• Bayesian neural networks for selection of drug sensitive genes
• Power-expected-posterior priors for generalized linear models
• Adjusting for selection bias in assessing treatment effect estimates from multiple subgroups
• Bayesian linear regression with sparse priors
• Testing for time variation in an unobserved components model for the U.S. economy
• Objective Bayesian comparison of constrained analysis of variance models
• Bayesian high-dimensional semi-parametric inference beyond sub-Gaussian errors
• Bayesian model selection for generalized linear mixed models
• Functional Bayesian networks for discovering causality from multivariate functional data
• Bayesian graphical models for modern biological applications
• Estimating the effects of fine particulate matter on 432 cardiovascular diseases using multi-outcome regression with tree-structured shrinkage
• Joint modeling of longitudinal relational data and exogenous variables
• An evaluation of alternative methods for testing hypotheses, from the perspective of Harold Jeffreys
• Empirical Bayes methods in classical and Bayesian inference
• Bayesian graphical regression
• Dynamic inverse prediction and sensitivity analysis with high-dimensional responses: application to climate-change vulnerability of biodiversity
• Semiparametric Bayesian inference for phage display data
• An objective Bayesian criterion to determine model prior probabilities
• High-dimensional Ising model selection with Bayesian information criteria
• Learning Bayesian networks: a copula approach for mixed-type data
• Frequentist properties of Bayesian multiplicity control for multiple testing of normal means
• Posterior contraction in sparse Bayesian factor models for massive covariance matrices
• A Bayesian model averaging approach for observational gene expression studies
• A simple method for comparing complex models: Bayesian model comparison for hierarchical multinomial processing tree models using Warp-III bridge sampling
• Spike and slab regression for nonstationary Gaussian linear mixed effects modeling of rapid disease progression
• Default Bayes factors for testing the (in)equality of several population variances
• A metropolized adaptive subspace algorithm for high-dimensional Bayesian variable selection
• Rejoinder by James Berger, Woncheol Jang, Surajit Ray, Luis R. Pericchi and Ingmar Visser
• The influence of misspecified covariance on false discovery control when using posterior probabilities
• Bayesian Edge Regression in Undirected Graphical Models to Characterize Interpatient Heterogeneity in Cancer
• Posterior consistency of \(g\)-prior for variable selection with a growing number of parameters
• Mixtures of \(g\)-priors in generalized linear models
• On model selection consistency of regularized M-estimators
• Unified screening for potential elevated adverse event risk and other associations
• Objective Bayesian model selection for spatial hierarchical models with intrinsic conditional autoregressive priors
• Objective Bayesian edge screening and structure selection for Ising networks
• Empirical Bayes methods in variable selection
• Profiling the effects of short time-course cold ischemia on tumor protein phosphorylation using a Bayesian approach
• A Bayesian model to identify multiple expression patterns with simultaneous FDR control for a multi-factor RNA-seq experiment
• Model Uncertainty Quantification in Cox Regression
• The scalable birth-death MCMC algorithm for mixed graphical model learning with application to genomic data integration
• Bayesian model selection for a linear model with grouped covariates
• Bayesian variable selection for survival data using inverse moment priors
• Objective Bayesian model selection for Cox regression

Describes a project that uses

Uses Software

• EBayesThresh

This page was built for publication: Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q605920)