Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means

DOI10.1214/08-AOS630MaRDI QIDQ2388977zbMATH OpenOpenAlexFDO

Authors Lawrence Brown, Eitan Greenshtein

Publication date 22 July 2009

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0908.1712

zbMATH Keywords

compound decisionempirical Bayessimulations

Mathematics Subject Classification ID

Empirical decision procedures; empirical Bayes procedures (62C12) Compound decision problems in statistical decision theory (62C25) Estimation in multivariate analysis (62H12)

Abstract: We consider the classical problem of estimating a vector $$ based on independent observations $Y_{i}simN(m{u}_i,1)$, $i=1,\mathrm{...},n$. Suppose $m{u}_i$, $i=1,\mathrm{...},n$ are independent realizations from a completely unknown $G$. We suggest an easily computed estimator $$, such that the ratio of its risk $$ with that of the Bayes procedure approaches 1. A related compound decision result is also obtained. Our asymptotics is of a triangular array; that is, we allow the distribution $G$ to depend on $n$. Thus, our theoretical asymptotic results are also meaningful in situations where the vector $$ is sparse and the proportion of zero coordinates approaches 1. We demonstrate the performance of our estimator in simulations, emphasizing sparse setups. In ``moderately-sparse situations, our procedure performs very well compared to known procedures tailored for sparse setups. It also adapts well to nonsparse situations.

Recommendations

• Asymptotically minimax empirical Bayes estimation of a sparse normal mean vector
• Estimating the mean of high valued observations in high dimensions
• Empirical Bayes estimators for high-dimensional sparse vectors
• Empirical Bayes thresholding: adapting to sparsity when it advantageous to do so
• On optimality of Bayesian testimation in the normal means problem

Cites work

• Admissible Estimators, Recurrent Diffusions, and Insoluble Boundary Value Problems
• Application of non parametric empirical Bayes estimation to high dimensional classification
• Asymptotic efficiency of simple decisions for the compound decision problem
• Compound decision theory and empirical Bayes methods
• General empirical Bayes wavelet methods and exactly adaptive minimax estimation
• General maximum likelihood empirical Bayes estimation of normal means
• scientific article; zbMATH DE number 3124366 (Why is no real title available?)
• scientific article; zbMATH DE number 3462965 (Why is no real title available?)
• scientific article; zbMATH DE number 1057577 (Why is no real title available?)
• scientific article; zbMATH DE number 3297736 (Why is no real title available?)
• scientific article; zbMATH DE number 3068128 (Why is no real title available?)
• Ideal spatial adaptation by wavelet shrinkage
• In-season prediction of batting averages: a field test of empirical Bayes and Bayes methodol\-ogies
• Needles and straw in haystacks: Empirical Bayes estimates of possibly sparse sequences
• Robbins, empirical Bayes and microarrays
• The Empirical Bayes Approach to Statistical Decision Problems
• Weak convergence and empirical processes. With applications to statistics

Cited in

(70)

• A deconvolution path for mixtures
• Simultaneous estimation based on empirical likelihood and general maximum likelihood estimation
• Needles and straw in a haystack: posterior concentration for possibly sparse sequences
• Deconvolution estimation of mixture distributions with boundaries
• Generalized maximum likelihood estimation of the mean of parameters of mixtures. With applications to sampling and to observational studies
• Mathematical foundations of machine learning. Abstracts from the workshop held March 21--27, 2021 (hybrid meeting)
• Empirical estimates for heteroscedastic hierarchical dynamic normal models
• Poisson mean vector estimation with nonparametric maximum likelihood estimation and application to protein domain data
• Statistical theory powering data science
• On the nonparametric maximum likelihood estimator for Gaussian location mixture densities with application to Gaussian denoising
• Panel forecasts of country-level Covid-19 infections
• A paradoxical argument about domination
• Nonparametric empirical Bayes improvement of shrinkage estimators with applications to time series
• Bayes, oracle Bayes and empirical Bayes
• Comment: Empirical Bayes, compound decisions and exchangeability
• Empirical Bayes thresholding: adapting to sparsity when it advantageous to do so
• General maximum likelihood empirical Bayes estimation of normal means
• Optimal shrinkage of eigenvalues in the spiked covariance model
• Estimating the mean and variance of a high-dimensional normal distribution using a mixture prior
• A guided random walk through some high dimensional problems
• Approximate repeated-measures shrinkage
• On optimality of Bayesian testimation in the normal means problem
• In-season prediction of batting averages: a field test of empirical Bayes and Bayes methodol\-ogies
• Optimal shrinkage estimation of mean parameters in family of distributions with quadratic variance
• Nonparametric empirical Bayes estimator in simultaneous estimation of Poisson means with application to mass spectrometry data
• A nonparametric empirical Bayes approach to adaptive minimax estimation
• Adaptive nonparametric empirical Bayes estimation via wavelet series: the minimax study
• scientific article; zbMATH DE number 1057577 (Why is no real title available?)
• On SURE estimates in hierarchical models assuming heteroscedasticity for both levels of a two-level normal hierarchical model
• Hunting for significance: Bayesian classifiers under a mixture loss function
• Asymptotically minimax empirical Bayes estimation of a sparse normal mean vector
• SURE Estimates for a Heteroscedastic Hierarchical Model
• Group-linear empirical Bayes estimates for a heteroscedastic normal mean
• SURE estimates for high dimensional classification
• Convex Optimization, Shape Constraints, Compound Decisions, and Empirical Bayes Rules
• Meta-analysis with fixed, unknown, study-specific parameters
• Optimal stopping and worker selection in crowdsourcing: an adaptive sequential probability ratio test framework
• A general framework for empirical Bayes estimation in discrete linear exponential family
• Empirical Bayes estimators for high-dimensional sparse vectors
• Efficient empirical Bayes estimates for risk parameters of Pareto distributions
• Adaptive sparse estimation with side information
• Simultaneous estimation of normal means with side information
• Improved shrinkage prediction under a spiked covariance structure
• Asymptotically optimal nonparametric empirical Bayes via predictive recursion
• Integrative genetic risk prediction using non-parametric empirical Bayes classification
• The Poisson Compound Decision Problem Revisited
• Estimation of a sparse group of sparse vectors
• Irrational Exuberance: Correcting Bias in Probability Estimates
• Confidence Intervals for Nonparametric Empirical Bayes Analysis
• Rejoinder: Confidence Intervals for Nonparametric Empirical Bayes Analysis
• Compound Sequential Change-point Detection in Parallel Data Streams
• A Compound Decision Approach to Covariance Matrix Estimation
• Forecasting with a panel Tobit model
• Nonparametric empirical Bayes estimation based on generalized Laguerre series
• A Regression Modeling Approach to Structured Shrinkage Estimation
• Empirical Bayes Mean Estimation With Nonparametric Errors Via Order Statistic Regression on Replicated Data
• Robust empirical Bayes confidence intervals
• High dimensional discriminant rules with shrinkage estimators of the covariance matrix and mean vector
• Unobserved Heterogeneity in Income Dynamics: An Empirical Bayes Perspective
• A locally adaptive shrinkage approach to false selection rate control in high-dimensional classification
• No need for an oracle: the nonparametric maximum likelihood decision in the compound decision problem is minimax
• Poisson empirical Bayes estimation: when does g-modeling beat f-modeling in theory (and in practice)?
• Optimal empirical Bayes estimation for the Poisson model via minimum-distance methods
• Stein estimator from a polar coordinate perspective
• Nonparametric empirical Bayes prediction in mixed models
• Estimating the mean of high valued observations in high dimensions
• Optimal shrinkage estimation of fixed effects in linear panel data models
• Approximate independence of permutation mixtures
• Forecasting with panel data: estimation uncertainty versus parameter heterogeneity
• A Fast Algorithm for Maximum Likelihood Estimation of Mixture Proportions Using Sequential Quadratic Programming

Describes a project that uses

Uses Software

• EBayesThresh

This page was built for publication: Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2388977)