Scalable Bayesian nonparametric regression via a Plackett-Luce model for conditional ranks

DOI10.1214/15-EJS1032MaRDI QIDQ309544zbMATH OpenOpenAlexWikidataFDO

Authors Tristan Gray-Davies, Francois Caron, Chris Holmes

Publication date 7 September 2016

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1506.07412, https://projecteuclid.org/euclid.ejs/1468849964

zbMATH Keywords

Bayesian nonparametricscomposite likelihoodDirichlet process mixturesPlackett-LucePólya tree

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to social sciences (62P25)

Abstract: We present a novel Bayesian nonparametric regression model for covariates X and continuous, real response variable Y. The model is parametrized in terms of marginal distributions for Y and X and a regression function which tunes the stochastic ordering of the conditional distributions F(y|x). By adopting an approximate composite likelihood approach, we show that the resulting posterior inference can be decoupled for the separate components of the model. This procedure can scale to very large datasets and allows for the use of standard, existing, software from Bayesian nonparametric density estimation and Plackett-Luce ranking estimation to be applied. As an illustration, we show an application of our approach to a US Census dataset, with over 1,300,000 data points and more than 100 covariates.

Recommendations

• Adaptive-modal Bayesian nonparametric regression
• Nonparametric Bayesian aggregation for massive data
• Adaptive Bayesian density regression for high-dimensional data
• A Bayesian nonparametric approach to inference for quantile regression
• A fully nonparametric modeling approach to binary regression

Cites work

• scientific article; zbMATH DE number 5849508 (Why is no real title available?)
• scientific article; zbMATH DE number 3152611 (Why is no real title available?)
• scientific article; zbMATH DE number 4100431 (Why is no real title available?)
• scientific article; zbMATH DE number 1738333 (Why is no real title available?)
• scientific article; zbMATH DE number 3385132 (Why is no real title available?)
• A Bayesian analysis of some nonparametric problems
• A nonparametric Bayes method for isotonic regression
• A note on pseudolikelihood constructed from marginal densities
• An ANOVA Model for Dependent Random Measures
• BART: Bayesian additive regression trees
• Bayesian Density Estimation and Inference Using Mixtures
• Bayesian Density Regression
• Bayesian Gaussian Copula Factor Models for Mixed Data
• Bayesian Inference for Linear Dynamic Models With Dirichlet Process Mixtures
• Bayesian Semiparametric Median Regression Modeling
• Bayesian Semiparametric Regression for Median Residual Life
• Bayesian composite marginal likelihoods
• Bayesian curve fitting using multivariate normal mixtures
• Bayesian inference from composite likelihoods, with an application to spatial extremes
• Bayesian nonparametric regression with varying residual density
• Dirichlet process mixtures of generalized linear models
• Extending the rank likelihood for semiparametric copula estimation
• Fundamentals of nonparametric Bayesian inference
• Gaussian processes for machine learning.
• Improving prediction from Dirichlet process mixtures via enrichment
• Kernel stick-breaking processes
• More aspects of Pólya tree distributions for statistical modelling
• Nonlinear models using Dirichlet process mixtures
• Nonparametric Bayes conditional distribution modeling with variable selection
• Nonparametric Bayesian data analysis
• On a class of Bayesian nonparametric estimates: I. Density estimates
• Order-Based Dependent Dirichlet Processes
• Polya trees and random distributions
• Prior distributions on spaces of probability measures
• Quantile pyramids for Bayesian nonparametrics
• Some aspects of Pólya tree distributions for statistical modelling
• The Bernstein-von Mises theorem for the proportional hazard model
• The multivariate beta process and an extension of the Pólya tree model

Cited in

(2)

• Bayesian analysis of rank data with covariates and heterogeneous rankers
• Bayesian approximate kernel regression with variable selection

Describes a project that uses

Uses Software

• BartPy
• DPpackage
• BayesTree
• bfa

This page was built for publication: Scalable Bayesian nonparametric regression via a Plackett-Luce model for conditional ranks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q309544)