Bayesian effect selection in structured additive distributional regression models
From MaRDI portal
Publication:2057331
Abstract: We propose a novel spike and slab prior specification with scaled beta prime marginals for the importance parameters of regression coefficients to allow for general effect selection within the class of structured additive distributional regression. This enables us to model effects on all distributional parameters for arbitrary parametric distributions, and to consider various effect types such as non-linear or spatial effects as well as hierarchical regression structures. Our spike and slab prior relies on a parameter expansion that separates blocks of regression coefficients into overall scalar importance parameters and vectors of standardised coefficients. Hence, we can work with a scalar quantity for effect selection instead of a possibly high-dimensional effect vector, which yields improved shrinkage and sampling performance compared to the classical normal-inverse-gamma prior. We investigate the propriety of the posterior, show that the prior yields desirable shrinkage properties, propose a way of eliciting prior parameters and provide efficient Markov Chain Monte Carlo sampling. Using both simulated and three large-scale data sets, we show that our approach is applicable for data with a potentially large number of covariates, multilevel predictors accounting for hierarchically nested data and non-standard response distributions, such as bivariate normal or zero-inflated Poisson.
Recommendations
- Effect Selection and Regularization in Structured Additive Distributional Regression
- Bayesian regularization and model choice in structured additive regression
- Bayesian structured variable selection in linear regression models
- A Bayesian approach to additive semiparametric regression
- Bayesian structured additive quantile regression
- Correcting for sample selection bias in Bayesian distributional regression models
- Bayesian inference for additive mixed quantile regression models
- Hyper-parameter selection in Bayesian structural equation models
- Bayesian variable selection in a finite mixture of linear mixed-effects models
Cites work
- scientific article; zbMATH DE number 1034042 (Why is no real title available?)
- scientific article; zbMATH DE number 6734253 (Why is no real title available?)
- scientific article; zbMATH DE number 2222295 (Why is no real title available?)
- A Bayesian hierarchical model for classification with selection of functional predictors
- A review of Bayesian variable selection methods: what, how and which
- Achieving shrinkage in a time-varying parameter model framework
- Bayes variable selection in semiparametric linear models
- Bayesian Variable Selection in Linear Regression
- Bayesian effect selection in structured additive distributional regression models
- Bayesian estimation of sparse signals with a continuous spike-and-slab prior
- Bayesian generalized additive models for location, scale, and shape for zero-inflated and overdispersed count data
- Bayesian identification, selection and estimation of semiparametric functions in high-dimensional additive models
- Bayesian linear regression with sparse priors
- Bayesian structured additive distributional regression with an application to regional income inequality in Germany
- Bayesian variable selection and estimation for group Lasso
- Conditions for posterior contraction in the sparse normal means problem
- Fast Stable Restricted Maximum Likelihood and Marginal Likelihood Estimation of Semiparametric Generalized Linear Models
- Gaussian Markov Random Fields
- Generalized Additive Models for Location, Scale and Shape
- Geoadditive Models
- Model uncertainty
- Multilevel structured additive regression
- Needles and straw in a haystack: posterior concentration for possibly sparse sequences
- Nonparametric Bayes conditional distribution modeling with variable selection
- Nonparametric regression using Bayesian variable selection
- On the beta prime prior for scale parameters in high-dimensional Bayesian regression models
- On the use of Cauchy prior distributions for Bayesian logistic regression
- Optimal predictive model selection.
- Penalising model component complexity: a principled, practical approach to constructing priors
- Scale-dependent priors for variance parameters in structured additive distributional regression
- Semiparametric Regression
- Simultaneous confidence bands for penalized~spline~estimators
- Simultaneous probability statements for Bayesian P-splines
- Spike and slab variable selection: frequentist and Bayesian strategies
- Spike-and-slab priors for function selection in structured additive regression models
- The scaled beta2 distribution as a robust prior for scales
- The spike-and-slab LASSO
- Tractable Bayesian variable selection: beyond normality
- Variable Selection and Model Averaging in Semiparametric Overdispersed Generalized Linear Models
Cited in
(13)- Bayesian structured additive distributional regression with an application to regional income inequality in Germany
- Effect Selection and Regularization in Structured Additive Distributional Regression
- Correcting for sample selection bias in Bayesian distributional regression models
- Bayesian effect selection in structured additive distributional regression models
- Boosting multivariate structured additive distributional regression models
- Modular regression -- a Lego system for building structured additive distributional regression models with tensor product interactions
- Spike-and-slab priors for function selection in structured additive regression models
- Scale-dependent priors for variance parameters in structured additive distributional regression
- Structured additive distributional regression for analysing landings per unit effort in fisheries research
- Bayesian effect fusion for categorical predictors
- A multilevel analysis of real estate valuation using distributional and quantile regression
- Bayesian discrete conditional transformation models
- Bayesian regularization and model choice in structured additive regression
Describes a project that uses
Uses Software
This page was built for publication: Bayesian effect selection in structured additive distributional regression models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057331)
