Variable selection via penalized credible regions with Dirichlet-Laplace global-local shrinkage priors

DOI10.1214/17-BA1076zbMath1407.62272arXiv1602.01160MaRDI QIDQ1631579

Howard D. Bondell, Yan Zhang

Publication date: 6 December 2018

Published in: Bayesian Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1602.01160

zbMATH Keywords

linear regressionvariable selectionposterior consistencyDirichlet-Laplaceglobal-local shrinkage priorhyperparameter tuningposterior credible region

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Linear regression; mixed models (62J05) Bayesian inference (62F15)

Related Items (7)

Bayesian Regression Using a Prior on the Model Fit: The R2-D2 Shrinkage Prior ⋮ Bayesian Approaches to Shrinkage and Sparse Estimation ⋮ Informative Bayesian neural network priors for weak signals ⋮ A novel Bayesian approach for variable selection in linear regression models ⋮ Computationally efficient inference in large Bayesian mixed frequency VARs ⋮ Supervised t-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification ⋮ Sparse linear mixed model selection via streamlined variational Bayes

Uses Software

• OSCAR

Cites Work

• Unnamed Item
• Unnamed Item
• A unified approach to model selection and sparse recovery using regularized least squares
• Empirical Bayes posterior concentration in sparse high-dimensional linear models
• The Adaptive Lasso and Its Oracle Properties
• Bayesian adaptive Lasso
• Bayesian linear regression with sparse priors
• Approximations of the eigenvalues of the covariance matrix of a first order autoregressive process
• Estimating the dimension of a model
• The horseshoe+ estimator of ultra-sparse signals
• Least angle regression. (With discussion)
• Spike and slab variable selection: frequentist and Bayesian strategies
• Estimation and variable selection with exponential weights
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• The Bayesian elastic net
• Inference with normal-gamma prior distributions in regression problems
• Calibration and empirical Bayes variable selection
• Posterior consistency in linear models under shrinkage priors
• The horseshoe estimator for sparse signals
• The Bayesian Lasso
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Consistent High-Dimensional Bayesian Variable Selection via Penalized Credible Regions
• Generalized double Pareto shrinkage
• Regularization and Variable Selection Via the Elastic Net
• Dirichlet–Laplace Priors for Optimal Shrinkage
• Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
• Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCAR

This page was built for publication: Variable selection via penalized credible regions with Dirichlet-Laplace global-local shrinkage priors