# Bayesian Variable Selection and Estimation Based on Global-Local Shrinkage Priors

@article{Tang2016BayesianVS, title={Bayesian Variable Selection and Estimation Based on Global-Local Shrinkage Priors}, author={Xueying Tang and Xiaofang Xu and Malay Ghosh and Prasenjit Ghosh}, journal={arXiv: Methodology}, year={2016} }

In this paper, we consider Bayesian variable selection problem of linear regression model with global-local shrinkage priors on the regression coefficients. We propose a variable selection procedure that select a variable if the ratio of the posterior mean to the ordinary least square estimate of the corresponding coefficient is greater than $1/2$. Under the assumption of orthogonal designs, we show that if the local parameters have polynomial-tailed priors, our proposed method enjoys the… Expand

#### 16 Citations

High-dimensional multivariate posterior consistency under global-local shrinkage priors

- Mathematics, Computer Science
- J. Multivar. Anal.
- 2018

This paper derives sufficient conditions for posterior consistency under the Bayesian multivariate linear regression framework and proves that the method achieves posterior consistency even when p>n and even whenp grows at nearly exponential rate with the sample size. Expand

Adaptive Bayesian Shrinkage Estimation Using Log-Scale Shrinkage Priors

- Mathematics, Computer Science
- ArXiv
- 2018

This paper proposes a new type of ultra-heavy tailed prior, called the log-$t$ prior, which exhibits the property that, irrespective of the choice of associated scale parameter, the induced marginal distribution over $\ beta_j$ always diverge at $\beta_j = 0$, and always possesses super-Cauchy tails. Expand

Nearly optimal Bayesian Shrinkage for High Dimensional Regression

- Mathematics
- 2017

During the past decade, shrinkage priors have received much attention in Bayesian analysis of high-dimensional data. In this paper, we study the problem for high-dimensional linear regression models.… Expand

The Bayesian adaptive lasso regression.

- Medicine, Computer Science
- Mathematical biosciences
- 2018

This paper considers a fully Bayesian treatment for the adaptive lasso that leads to a new Gibbs sampler with tractable full conditional posteriors and shows that the new approach performs well in comparison to the existing Bayesian and non-Bayesian approaches. Expand

Ultra high-dimensional multivariate posterior contraction rate under shrinkage priors

- Mathematics
- Journal of Multivariate Analysis
- 2022

In recent years, shrinkage priors have received much attention in high-dimensional data analysis from a Bayesian perspective. Compared with widely used spike-and-slab priors, shrinkage priors have… Expand

Bayesian Fusion Estimation via t Shrinkage

- Computer Science, Mathematics
- Sankhya A
- 2019

This work proposes to impose heavy-tail shrinkage prior, e.g., $t$ prior, on the differences of successive parameter entries, and such a fusion prior will shrink successive differences towards zero and hence induce posterior blocking. Expand

Precision Matrix Estimation under the Horseshoe-like Prior-Penalty Dual

- Mathematics
- 2021

The problem of precision matrix estimation in a multivariate Gaussian model is fundamental to network estimation. Although there exist both Bayesian and frequentist approaches to this, it is… Expand

Group Inverse-Gamma Gamma Shrinkage for Sparse Regression with Block-Correlated Predictors

- Mathematics
- 2021

Heavy-tailed continuous shrinkage priors, such as the horseshoe prior, are widely used for sparse estimation problems. However, there is limited work extending these priors to predictors with… Expand

Spatially varying sparsity in dynamic regression models

- Computer Science
- 2020

A Bayesian spatially dynamic selection model based on spatial normal-gamma process (SNGP), which pursues spatial varying sparsity in dynamic regression models, is proposed, which has both good estimation performance and selection performance. Expand

Sparse Linear Mixed Model Selection via Streamlined Variational Bayes

- Mathematics
- 2021

Linear mixed models are a versatile statistical tool to study data by accounting for fixed effects and random effects from multiple sources of variability. In many situations, a large number of… Expand

#### References

SHOWING 1-10 OF 42 REFERENCES

Bayesian variable selection with shrinking and diffusing priors

- Mathematics
- 2014

We consider a Bayesian approach to variable selection in the presence of high dimensional covariates based on a hierarchical model that places prior distributions on the regression coefficients as… Expand

Bayesian Variable Selection and Estimation for Group Lasso

- Mathematics
- 2015

The paper revisits the Bayesian group lasso and uses spike and slab priors for group variable selection. In the process, the connection of our model with penalized regression is demonstrated, and the… Expand

The Bayesian Lasso

- Mathematics
- 2008

The Lasso estimate for linear regression parameters can be interpreted as a Bayesian posterior mode estimate when the regression parameters have independent Laplace (i.e., double-exponential) priors.… Expand

Shrink Globally, Act Locally: Sparse Bayesian Regularization and Prediction

- Mathematics
- 2012

We study the classic problem of choosing a prior distribution for a location parameter β = (β1, . . . , βp) as p grows large. First, we study the standard “global-local shrinkage” approach, based on… Expand

BAYESIAN LINEAR REGRESSION WITH SPARSE PRIORS

- Mathematics
- 2015

We study full Bayesian procedures for high-dimensional linear regression under sparsity constraints. The prior is a mixture of point masses at zero and continuous distributions. Under compatibility… Expand

Bayesian Variable Selection in Linear Regression

- Mathematics
- 1988

Abstract This article is concerned with the selection of subsets of predictor variables in a linear regression model for the prediction of a dependent variable. It is based on a Bayesian approach,… Expand

Inference with normal-gamma prior distributions in regression problems

- Mathematics
- 2010

This paper considers the efiects of placing an absolutely continuous prior distribution on the regression coe-cients of a linear model. We show that the posterior expectation is a matrix-shrunken… Expand

Alternative prior distributions for variable selection with very many more variables than observations

- Mathematics
- 2005

The problem of variable selection in regression and the generalised linear model is addressed.
We adopt a Bayesian approach with priors for the regression coefficients that are
scale mixtures of… Expand

Bayesian Model Selection in High-Dimensional Settings

- Medicine, Mathematics
- Journal of the American Statistical Association
- 2012

Modifications of Bayesian model selection methods by imposing nonlocal prior densities on model parameters are proposed and it is demonstrated that these model selection procedures perform as well or better than commonly used penalized likelihood methods in a range of simulation settings. Expand

Consistent High-Dimensional Bayesian Variable Selection via Penalized Credible Regions

- Computer Science, Medicine
- Journal of the American Statistical Association
- 2012

This work proposes a conjugate prior only on the full model parameters and use sparse solutions within posterior credible regions to perform selection, and shows that these sparse solutions can be computed via existing algorithms. Expand