On the use of Markovian stick-breaking priors

DOI10.1090/CONM/774/15571zbMATH Open1485.60074arXiv2108.10849OpenAlexW3215655308MaRDI QIDQ5024705FDOQ5024705

Authors: William Lippitt, Sunder Sethuraman 

Publication date: 27 January 2022

Published in: Stochastic Processes and Functional Analysis (Search for Journal in Brave)

Abstract: In [10], a `Markovian stick-breaking' process which generalizes the Dirichlet process $(mu,heta)$ with respect to a discrete base space $mathfrakX$ was introduced. In particular, a sample from from the `Markovian stick-breaking' processs may be represented in stick-breaking form $su{m}_{igeq1}{P}_{i}delt{a}_{T_i}$ where $T_i$ is a stationary, irreducible Markov chain on $mathfrakX$ with stationary distribution $mu$, instead of i.i.d. $T_i$ each distributed as $mu$ as in the Dirichlet case, and $P_i$ is a GEM$(heta)$ residual allocation sequence. Although the motivation in [10] was to relate these Markovian stick-breaking processes to empirical distributional limits of types of simulated annealing chains, these processes may also be thought of as a class of priors in statistical problems. The aim of this work in this context is to identify the posterior distribution and to explore the role of the Markovian structure of $T_i$ in some inference test cases.

Full work available at URL: https://arxiv.org/abs/2108.10849

Recommendations

• Stick-breaking processes, clumping, and Markov chain occupation laws
• Stick-Breaking Processes With Exchangeable Length Variables
• Gibbs Sampling Methods for Stick-Breaking Priors
• Stick-breaking autoregressive processes
• Some further developments for stick-breaking priors: finite and infinite clustering and classifica\-tion

zbMATH Keywords

Markovian stick-breaking processs

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Random measures (60G57) Dirichlet form methods in Markov processes (60J46)

Cites Work

• Bayesian density estimation using bernstein polynomials
• Bayesian Density Estimation and Inference Using Mixtures
• Generalized Dirichlet distribution in Bayesian analysis
• Bayesian nonparametric data analysis
• Logistic-Normal Distributions: Some Properties and Uses
• A Bayesian analysis of some nonparametric problems
• Analysis of ordinal categorical data.
• Fundamentals of nonparametric Bayesian inference
• Bayesian Models for Categorical Data
• Title not available (Why is that?)
• Ferguson distributions via Polya urn schemes
• Bayesian Statistical Modelling
• On the Asymptotic Behavior of Bayes' Estimates in the Discrete Case
• Some aspects of Pólya tree distributions for statistical modelling
• Title not available (Why is that?)
• Prior induction in log-linear models for general contingency table analysis.
• A Bayesian approach for the estimation of probability distributions under finite sample space
• Filtered-Variate Prior Distributions for Histogram Smoothing
• Title not available (Why is that?)
• Bayesian inference for categorical data analysis
• Title not available (Why is that?)
• A partition Dirichlet process model for functional data analysis
• Occupation laws for some time-nonhomogeneous Markov chains
• Bayesian estimation methods for contingency tables
• On the topological support of species sampling priors
• Bayesian methods. An analysis for statisticians and interdisciplinary researchers
• Stick-breaking processes, clumping, and Markov chain occupation laws

Cited In (8)

• Evaluating default priors with a generalization of Eaton's Markov chain
• Stick-breaking autoregressive processes
• Markov jump random c.d.f.'s and their posterior distributions
• Stationarity and Inference in Multistate Promoter Models of Stochastic Gene Expression via Stick-Breaking Measures
• A new proof of the stick-breaking representation of Dirichlet processes
• Stick-breaking processes, clumping, and Markov chain occupation laws
• Stick-Breaking Processes With Exchangeable Length Variables
• Gibbs Sampling Methods for Stick-Breaking Priors

This page was built for publication: On the use of Markovian stick-breaking priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5024705)