Implicit copulas from Bayesian regularized regression smoothers

DOI10.1214/18-BA1138zbMATH Open1435.62178arXiv1804.10397OpenAlexW3098892885MaRDI QIDQ2290705FDOQ2290705

Authors: Nadja Klein, Michael Stanley Smith 

Publication date: 29 January 2020

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

Abstract: We show how to extract the implicit copula of a response vector from a Bayesian regularized regression smoother with Gaussian disturbances. The copula can be used to compare smoothers that employ different shrinkage priors and function bases. We illustrate with three popular choices of shrinkage priors --- a pairwise prior, the horseshoe prior and a g prior augmented with a point mass as employed for Bayesian variable selection --- and both univariate and multivariate function bases. The implicit copulas are high-dimensional, have flexible dependence structures that are far from that of a Gaussian copula, and are unavailable in closed form. However, we show how they can be evaluated by first constructing a Gaussian copula conditional on the regularization parameters, and then integrating over these. Combined with non-parametric margins the regularized smoothers can be used to model the distribution of non-Gaussian univariate responses conditional on the covariates. Efficient Markov chain Monte Carlo schemes for evaluating the copula are given for this case. Using both simulated and real data, we show how such copula smoothing models can improve the quality of resulting function estimates and predictive distributions.

Full work available at URL: https://arxiv.org/abs/1804.10397

Recommendations

• Efficient Bayesian inference for Gaussian copula regression models
• Bayesian nonparametric estimation of a copula
• Gaussian copula marginal regression
• Bayesian nonparametric inference for a multivariate copula function
• Bayesian variable selection for non‐Gaussian responses: a marginally calibrated copula approach

zbMATH Keywords

distributional regressionhorseshoe priorpenalized splinesregression splinesradial basis

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Generalized linear models (logistic models) (62J12) Numerical computation using splines (65D07)

Cites Work

• Bayesian smoothing and regression for longitudinal, spatial and event history data.
• Semiparametric Regression
• Gaussian Markov Random Fields
• Bayesian Gaussian Copula Factor Models for Mixed Data
• Title not available (Why is that?)
• Asymptotic efficiency of the two-stage estimation method for copula-based models
• The horseshoe estimator for sparse signals
• Multivariate Dispersion Models Generated From Gaussian Copula
• Spike-and-slab priors for function selection in structured additive regression models
• Simultaneous probability statements for Bayesian P-splines
• An introduction to copulas.
• Nonparametric regression using Bayesian variable selection
• Hedonic housing prices and the demand for clean air
• Model uncertainty
• The t Copula and Related Copulas
• Mixtures of g Priors for Bayesian Variable Selection
• 10.1162/15324430152748236
• Parsimonious Covariance Matrix Estimation for Longitudinal Data
• Scale-dependent priors for variance parameters in structured additive distributional regression
• Generalized Additive Models for Location, Scale and Shape
• Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem
• The meta-elliptical distributions with given marginals
• Bayesian structured additive distributional regression with an application to regional income inequality in Germany
• Bayesian inference for conditional copulas using Gaussian process single index models
• Approximate Bayesian inference in semiparametric copula models
• Dependence Calibration in Conditional Copulas: A Nonparametric Approach
• In mixed company: Bayesian inference for bivariate conditional copula models with discrete and continuous outcomes
• Title not available (Why is that?)

Cited In (4)

• Marginally Calibrated Deep Distributional Regression
• Bayesian variable selection for non‐Gaussian responses: a marginally calibrated copula approach
• Bayesian Inference for Regression Copulas
• Marginally calibrated response distributions for end-to-end learning in autonomous driving

Uses Software

• BayesX
• SemiPar
• bfa
• GAMLSS
• DPpackage

This page was built for publication: Implicit copulas from Bayesian regularized regression smoothers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2290705)