Bayesian variable selection for multioutcome models through shared shrinkage
From MaRDI portal
Abstract: Variable selection over a potentially large set of covariates in a linear model is quite popular. In the Bayesian context, common prior choices can lead to a posterior expectation of the regression coefficients that is a sparse (or nearly sparse) vector with a few non-zero components, those covariates that are most important. This article extends the global-local shrinkage idea to a scenario where one wishes to model multiple response variables simultaneously. Here, we have developed a variable selection method for a K-outcome model (multivariate regression) that identifies the most important covariates across all outcomes. The prior for all regression coefficients is a mean zero normal with coefficient-specific variance term that consists of a predictor-specific factor (shared local shrinkage parameter) and a model-specific factor (global shrinkage term) that differs in each model. The performance of our modeling approach is evaluated through simulation studies and a data example.
Recommendations
- Shared Bayesian variable shrinkage in multinomial logistic regression
- Bayesian variable selection for mixed effects model with shrinkage prior
- Bayesian variable selection with shrinking and diffusing priors
- Multivariate Bayesian Variable Selection and Prediction
- Bayesian shrinkage methods for partially observed data with many predictors
- Bayesian Semiparametric Multiple Shrinkage
- Variable selection using shrinkage priors
- Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem
- Variable Selection with Shrinkage Priors via Sparse Posterior Summaries
Cited in
(10)- Input selection and shrinkage in multiresponse linear regression
- Shared Bayesian variable shrinkage in multinomial logistic regression
- A global-local approach for detecting hotspots in multiple-response regression
- Multivariate Bayesian variable selection exploiting dependence structure among outcomes: application to air pollution effects on DNA methylation
- Decoupling shrinkage and selection in Bayesian linear models: a posterior summary perspective
- Global–local shrinkage multivariate logit-beta priors for multiple response-type data
- A Comparison of Bayesian Multivariate Versus Univariate Normal Regression Models for Prediction
- Cross-cohort mixture analysis: a data integration approach with applications on gestational age and DNA-methylation-derived gestational age acceleration metrics
- Bayesian modeling of cancer outcomes using genetic variables assisted by pathological imaging data
- Two-step mixed-type multivariate Bayesian sparse variable selection with shrinkage priors
This page was built for publication: Bayesian variable selection for multioutcome models through shared shrinkage
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4994817)
