Marginally specified priors for non-parametric Bayesian estimation

DOI10.1111/RSSB.12059MaRDI QIDQ5379898zbMATH OpenOpenAlexWikidataFDO

Authors David C. Kessler, Peter D. Hoff, David Dunson

Publication date 14 June 2019

Published in Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1204.6505

zbMATH Keywords

contingency tablesdensity estimationDirichlet process mixture modelmultivariate unordered categorical datanon-informative priorprior elicitationsparse data

Mathematics Subject Classification ID

Bayesian inference (62F15) Nonparametric estimation (62G05) Density estimation (62G07) Estimation in multivariate analysis (62H12) Contingency tables (62H17)

Abstract: Prior specification for nonparametric Bayesian inference involves the difficult task of quantifying prior knowledge about a parameter of high, often infinite, dimension. Realistically, a statistician is unlikely to have informed opinions about all aspects of such a parameter, but may have real information about functionals of the parameter, such the population mean or variance. This article proposes a new framework for nonparametric Bayes inference in which the prior distribution for a possibly infinite-dimensional parameter is decomposed into two parts: an informative prior on a finite set of functionals, and a nonparametric conditional prior for the parameter given the functionals. Such priors can be easily constructed from standard nonparametric prior distributions in common use, and inherit the large support of the standard priors upon which they are based. Additionally, posterior approximations under these informative priors can generally be made via minor adjustments to existing Markov chain approximation algorithms for standard nonparametric prior distributions. We illustrate the use of such priors in the context of multivariate density estimation using Dirichlet process mixture models, and in the modeling of high-dimensional sparse contingency tables.

Recommendations

• Nonparametric Bayesian inference for multivariate density functions using Feller priors
• A bayesian nonparametric density estimator
• Nonparametric Bayesian data analysis
• Prior processes and their applications. Nonparametric Bayesian estimation
• Bayesian Nonparametric Inference for Random Distributions and Related Functions

Cited in

(9)

• The dependent Dirichlet process and related models
• Bayesian learning for a class of priors with prescribed marginals
• Moment conditions and Bayesian non-parametrics
• Bayesian Inference with Specified Prior Marginals
• Marginal Inferential Models: Prior-Free Probabilistic Inference on Interest Parameters
• Nonparametric Bayesian inference for multivariate density functions using Feller priors
• Specification of the Base Measure of Nonparametric Priors via Random Means
• Random probability measures with fixed mean distributions
• Marginally constrained nonparametric Bayesian inference through Gaussian processes

This page was built for publication: Marginally specified priors for non-parametric Bayesian estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5379898)