Mode jumping MCMC for Bayesian variable selection in GLMM

DOI10.1016/J.CSDA.2018.05.020zbMATH Open1469.62082arXiv1604.06398OpenAlexW2806191366MaRDI QIDQ1663135FDOQ1663135

Aliaksandr Hubin, Geir Storvik

Publication date: 21 August 2018

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Abstract: Generalized linear mixed models (GLMM) are used for inference and prediction in a wide range of different applications providing a powerful scientific tool. An increasing number of sources of data are becoming available, introducing a variety of candidate explanatory variables for these models. Selection of an optimal combination of variables is thus becoming crucial. In a Bayesian setting, the posterior distribution of the models, based on the observed data, can be viewed as a relevant measure for the model evidence. The number of possible models increases exponentially in the number of candidate variables. Moreover, the space of models has numerous local extrema in terms of posterior model probabilities. To resolve these issues a novel MCMC algorithm for the search through the model space via efficient mode jumping for GLMMs is introduced. The algorithm is based on that marginal likelihoods can be efficiently calculated within each model. It is recommended that either exact expressions or precise approximations of marginal likelihoods are applied. The suggested algorithm is applied to simulated data, the famous U.S. crime data, protein activity data and epigenetic data and is compared to several existing approaches.

Full work available at URL: https://arxiv.org/abs/1604.06398

zbMATH Keywords

Bayesian model averagingcombinatorial optimizationgeneralized linear mixed modelsBayesian variable selectionauxiliary variables MCMChigh performance computations

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Generalized linear models (logistic models) (62J12)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Bayesian Measures of Model Complexity and Fit
• Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
• Variational approximations in Bayesian model selection for finite mixture distributions
• The pseudo-marginal approach for efficient Monte Carlo computations
• Optimal predictive model selection.
• Generalized linear mixed models. Modern concepts, methods and applications.
• Marginal Likelihood from the Gibbs Output
• Accurate Approximations for Posterior Moments and Marginal Densities
• Bayesian Model Averaging for Linear Regression Models
• Particle Markov Chain Monte Carlo Methods
• Bayesian Graphical Models for Discrete Data
• Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator
• SMC2: An Efficient Algorithm for Sequential Analysis of State Space Models
• Approximate Bayesian computational methods
• Bayesian fractional polynomials
• Equi-energy sampler with applications in statistical inference and statistical mechanics
• Marginal Likelihood From the Metropolis–Hastings Output
• Mode jumping proposals in MCMC
• Multi-Domain Sampling With Applications to Structural Inference of Bayesian Networks
• Multiple shrinkage and subset selection in wavelets
• A double Metropolis–Hastings sampler for spatial models with intractable normalizing constants
• An introduction to variational methods for graphical models
• The Multiple-Try Method and Local Optimization in Metropolis Sampling
• Models for parallel and distributed computation. Theory, algorithmic techniques and application
• On the flexibility of Metropolis-Hastings acceptance probabilities in auxiliary variable proposal generation
• A Split-and-Merge Bayesian Variable Selection Approach for Ultrahigh Dimensional Regression
• Improving the acceptance rate of reversible jump MCMC proposals
• Methods for Binary Multidimensional Scaling

Cited In (6)

• Markov chain Monte Carlo with the integrated nested Laplace approximation
• FBMS
• Reversible jump Markov chain Monte Carlo algorithms for Bayesian variable selection in logistic mixed models
• Marginally Calibrated Deep Distributional Regression
• A subsampling approach for Bayesian model selection
• Mode jumping proposals in MCMC

Uses Software

• R-INLA
• ESS++

This page was built for publication: Mode jumping MCMC for Bayesian variable selection in GLMM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663135)