Bayesian semiparametric multivariate density deconvolution via stochastic rotation of replicates

DOI10.1016/J.CSDA.2023.107706arXiv2107.06436OpenAlexW3183032577MaRDI QIDQ6168913FDOQ6168913

Authors: Arkaprava Roy, Abhra Sarkar 

Publication date: 11 July 2023

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Abstract: We consider the problem of multivariate density deconvolution where the distribution of a random vector needs to be estimated from replicates contaminated with conditionally heteroscedastic measurement errors. We propose a conceptually straightforward yet fundamentally novel and highly robust approach to multivariate density deconvolution by stochastically rotating the replicates toward the corresponding true latent values. We also address the additionally significantly challenging problem of accommodating conditionally heteroscedastic measurement errors in this newly introduced framework. We take a Bayesian route to estimation and inference, implemented via an efficient Markov chain Monte Carlo algorithm, appropriately accommodating uncertainty in all aspects of our analysis. Asymptotic convergence guarantees for the method are also established. We illustrate the method's empirical efficacy through simulation experiments and its practical utility in estimating the long-term joint average intakes of different dietary components from their measurement error contaminated 24-hour dietary recalls.

Full work available at URL: https://arxiv.org/abs/2107.06436

Recommendations

• Bayesian semiparametric multivariate density deconvolution
• Bayesian Copula Density Deconvolution for Zero-Inflated Data in Nutritional Epidemiology
• Density estimation with replicate heteroscedastic measurements
• Bivariate kernel deconvolution with panel data
• scientific article; zbMATH DE number 5816778

zbMATH Keywords

copulaMarkov chain Monte Carlomeasurement errorHamiltonian Monte CarloStiefel manifoldnutritional epidemiologydensity deconvolutionvon Mises-Fisher distributionstochastic rotation

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Cites Work

• MCMC using Hamiltonian dynamics
• Bayesian Density Estimation and Inference Using Mixtures
• Finite mixture and Markov switching models.
• Measurement Error in Nonlinear Models
• Bayes Factors
• Unitary Triangularization of a Nonsymmetric Matrix
• A practical guide to splines
• On deconvolution with repeated measurements
• Deconvolving kernel density estimators
• Title not available (Why is that?)
• On the optimal rates of convergence for nonparametric deconvolution problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• A new multivariate measurement error model with zero-inflated dietary data, and its application to dietary assessment
• Density Estimation in the Presence of Heteroscedastic Measurement Error
• The Efficient Generation of Random Orthogonal Matrices with an Application to Condition Estimators
• Maximum likelihood estimators for the matrix von Mises-Fisher and Bingham distributions
• Orientation statistics
• A Hierarchical Eigenmodel for Pooled Covariance Estimation
• Anisotropic adaptive kernel deconvolution
• Title not available (Why is that?)
• Consistent deconvolution in density estimation
• Nonparametric estimation of the measurement error model using multiple indicators.
• Multiscale inference for multivariate deconvolution
• Deconvolution density estimation on \(\text{SO}(N)\)
• Measurement error. Models, methods and applications
• On a nonparametric recursive estimator of the mixing distribution
• Multivariate probability density deconvolution for stationary random processes
• Extreme deconvolution: inferring complete distribution functions from noisy, heterogeneous and incomplete observations
• Title not available (Why is that?)
• Optimal bandwidth selection for multivariate kernel deconvolution density estimation
• Semiparametric density deconvolution
• Bayesian semiparametric multivariate density deconvolution
• A deconvolution path for mixtures
• Latent surface models for networks using aggregated relational data
• Estimating Densities with Non-Linear Support by Using Fisher–Gaussian Kernels
• Bayesian Copula Density Deconvolution for Zero-Inflated Data in Nutritional Epidemiology

This page was built for publication: Bayesian semiparametric multivariate density deconvolution via stochastic rotation of replicates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6168913)