Adaptive density estimation based on a mixture of gammas

DOI10.1214/17-EJS1247zbMATH Open1362.62076arXiv1605.08467MaRDI QIDQ521332FDOQ521332

Authors: Natalia Bochkina, Judith Rousseau 

Publication date: 7 April 2017

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

Abstract: We consider the problem of Bayesian density estimation on the positive semiline for possibly unbounded densities. We propose a hierarchical Bayesian estimator based on the gamma mixture prior which can be viewed as a location mixture. We study convergence rates of Bayesian density estimators based on such mixtures. We construct approximations of the local H"older densities, and of their extension to unbounded densities, to be continuous mixtures of gamma distributions, leading to approximations of such densities by finite mixtures. These results are then used to derive posterior concentration rates, with priors based on these mixture models. The rates are minimax (up to a log n term) and since the priors are independent of the smoothness the rates are adaptive to the smoothness.

Full work available at URL: https://arxiv.org/abs/1605.08467

Recommendations

• scientific article; zbMATH DE number 5290366
• scientific article; zbMATH DE number 802872
• On adaptive estimation of probability density functions
• Adaptive Estimation of a Conditional Density
• \(\mathbb{L}_p\) adaptive density estimation in a \(\beta\) mixing framework
• Adaptive density estimation of stationary \(\beta\)-mixing and \(\tau\)-mixing processes
• Adaptive Dantzig density estimation
• Adaptive density estimation on bounded domains under mixing conditions

zbMATH Keywords

density estimationDirichlet processadaptive estimationrate of contractionBayesian nonparametric estimation[https://portal.mardi4nfdi.de/w/index.php?title=+Special%3ASearch&search=local+H%EF%BF%BD%EF%BF%BDlder+class&go=Go local H��lder class]mixture priorunbounded density

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Cited In (8)

• Estimating Income Distributions Using a Mixture of Gamma Densities
• \(\mathbb{L}_p\) adaptive density estimation in a \(\beta\) mixing framework
• Rates of convergence for the posterior distributions of mixtures of betas and adaptive nonparametric estimation of the density
• Bayesian high-dimensional semi-parametric inference beyond sub-Gaussian errors
• Adaptive Bayesian density estimation with location-scale mixtures
• Title not available (Why is that?)
• Finite mixture-of-gamma distributions: estimation, inference, and model-based clustering
• On predictive density estimation for gamma models with parametric constraints

This page was built for publication: Adaptive density estimation based on a mixture of gammas

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q521332)