Bayesian inference with dependent normalized completely random measures

DOI10.3150/13-BEJ521zbMATH Open1309.60048arXiv1407.0482MaRDI QIDQ396004FDOQ396004

Authors: Bernardo Nipoti, A. Lijoi, I. Prünster 

Publication date: 8 August 2014

Published in: Bernoulli (Search for Journal in Brave)

Abstract: The proposal and study of dependent prior processes has been a major research focus in the recent Bayesian nonparametric literature. In this paper, we introduce a flexible class of dependent nonparametric priors, investigate their properties and derive a suitable sampling scheme which allows their concrete implementation. The proposed class is obtained by normalizing dependent completely random measures, where the dependence arises by virtue of a suitable construction of the Poisson random measures underlying the completely random measures. We first provide general distributional results for the whole class of dependent completely random measures and then we specialize them to two specific priors, which represent the natural candidates for concrete implementation due to their analytic tractability: the bivariate Dirichlet and normalized $sigma$-stable processes. Our analytical results, and in particular the partially exchangeable partition probability function, form also the basis for the determination of a Markov Chain Monte Carlo algorithm for drawing posterior inferences, which reduces to the well-known Blackwell--MacQueen P'{o}lya urn scheme in the univariate case. Such an algorithm can be used for density estimation and for analyzing the clustering structure of the data and is illustrated through a real two-sample dataset example.

Full work available at URL: https://arxiv.org/abs/1407.0482

Recommendations

• Bayesian inference in the presence of intractable normalizing functions
• Bayesian inference for the extremal dependence
• Bayesian indirect inference for models with intractable normalizing functions
• Bayesian computation for statistical models with intractable normalizing constants
• Posterior Analysis for Normalized Random Measures with Independent Increments
• Nonparametric Bayes inference on conditional independence
• Compound random measures and their use in Bayesian non-parametrics
• Exact bayesian inference for normal hierarchical models
• Bayes estimates of estimable parameters with a direchlet invariant process

zbMATH Keywords

Dirichlet processcompletely random measuredependent Poisson processes[https://portal.mardi4nfdi.de/w/index.php?title=+Special%3ASearch&search=generalized+P%EF%BF%BD%EF%BF%BDlya+urn+scheme&go=Go generalized P��lya urn scheme]infinitely divisible vectornormalized \(\sigma\)-stable processpartially exchangeable random partition

Mathematics Subject Classification ID

Bayesian inference (62F15) Random measures (60G57)

Cites Work

• Bayesian Density Estimation and Inference Using Mixtures
• On the support of MacEachern's dependent Dirichlet processes and extensions
• Table of integrals, series, and products. Translated from the Russian. Translation edited and with a preface by Alan Jeffrey and Daniel Zwillinger. With one CD-ROM (Windows, Macintosh and UNIX)
• Estimating normal means with a conjugate style dirichlet process prior
• Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems
• Nonparametric Bayesian data analysis
• A Bayesian analysis of some nonparametric problems
• A Method for Combining Inference Across Related Nonparametric Bayesian Models
• A Multivariate Faa di Bruno Formula with Applications
• An introduction to the theory of point processes
• Combinatorial stochastic processes. Ecole d'Eté de Probabilités de Saint-Flour XXXII -- 2002.
• A bivariate beta distribution.
• Distributional results for means of normalized random measures with independent increments
• Posterior Analysis for Normalized Random Measures with Independent Increments
• Title not available (Why is that?)
• Gibbs Sampling Methods for Stick-Breaking Priors
• Title not available (Why is that?)
• The sampling theory of selectively neutral alleles
• Conjugacy as a Distinctive Feature of the Dirichlet Process
• Vectors of two-parameter Poisson-Dirichlet processes
• Projective limit random probabilities on Polish spaces
• A class of bivariate Poisson processes
• Bayesian Poisson process partition calculus with an application to Bayesian Lévy moving averages
• Title not available (Why is that?)
• Title not available (Why is that?)
• Efficient MCMC schemes for robust model extensions using encompassing Dirichlet process mixture models
• On Bayesian nonparametric modelling of two correlated distributions

Cited In (50)

• Sampling hierarchies of discrete random structures
• Discussion of ``On simulation and properties of the stable law by L. Devroye and L. James
• Modeling for dynamic ordinal regression relationships: an application to estimating maturity of rockfish in California
• The dependent Dirichlet process and related models
• Bayesian computation for statistical models with intractable normalizing constants
• Nonexchangeable random partition models for microclustering
• A class of dependent Dirichlet processes via latent multinomial processes
• Bayesian modeling via discrete nonparametric priors
• Compound vectors of subordinators and their associated positive Lévy copulas
• Dependent mixture models: clustering and borrowing information
• A vector of Dirichlet processes
• Correlated random measures
• Modelling and computation using NCoRM mixtures for density regression
• A blocked Gibbs sampler for NGG-mixture models via a priori truncation
• A class of hazard rate mixtures for combining survival data from different experiments
• Dependent Bayesian nonparametric modeling of compositional data using random Bernstein polynomials
• Compound random measures and their use in Bayesian non-parametrics
• The semi-hierarchical Dirichlet process and its application to clustering homogeneous distributions
• Importance conditional sampling for Pitman-Yor mixtures
• Multiscale stick-breaking mixture models
• Rejoinder on the normalized maximum likelihood and Bayesian decision theory: reply to Grünwald and Navarro (2009)
• Latent nested nonparametric priors (with discussion)
• Survival analysis via hierarchically dependent mixture hazards
• Random density functions with common atoms and pairwise dependence
• Dependent mixtures of geometric weights priors
• Beta-product dependent Pitman-Yor processes for Bayesian inference
• A Wasserstein Index of Dependence for Random Measures
• Nonparametric Bayesian inference in applications
• Vectors of two-parameter Poisson-Dirichlet processes
• Measuring dependence in the Wasserstein distance for Bayesian nonparametric models
• Dependent mixtures of Dirichlet processes
• Distribution theory for hierarchical processes
• A unified approach to hierarchical random measures
• Modeling with normalized random measure mixture models
• Integrability conditions for compound random measures
• Posterior Analysis for Normalized Random Measures with Independent Increments
• An ANOVA Model for Dependent Random Measures
• Model selection for maternal hypertensive disorders with symmetric hierarchical Dirichlet processes
• Thinned completely random measures with applications in competing risks models
• Scalable Bayesian nonparametric measures for exploring pairwise dependence via Dirichlet process mixtures
• Theory and computations for the Dirichlet process and related models: an overview
• Clustering dynamics in a class of normalised generalised gamma dependent priors
• A multivariate extension of a vector of two-parameter Poisson-Dirichlet processes
• On the normalized maximum likelihood and Bayesian decision theory
• Transport distances on random vectors of measures: recent advances in Bayesian nonparametrics
• Representation theorems for partially exchangeable random variables
• Bayesian mixed effects models for zero-inflated compositions in microbiome data analysis
• Sequential Monte Carlo methods for mixtures with normalized random measures with independent increments priors
• On quasi-infinitely divisible random measures
• Survival Regression Models With Dependent Bayesian Nonparametric Priors

This page was built for publication: Bayesian inference with dependent normalized completely random measures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q396004)