Shrinkage estimation in multilevel normal models

DOI10.1214/11-STS363MaRDI QIDQ2634658zbMATH OpenFDO

Authors Carl Morris, Martin Lysy

Publication date 18 February 2016

Published in Statistical Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1203.5610, https://projecteuclid.org/euclid.ss/1331729986

zbMATH Keywords

empirical Bayeshierarchical modelmodel-II evaluationsStein's harmonic priorunequal variances

Mathematics Subject Classification ID

Point estimation (62F10) Bayesian inference (62F15) Estimation in multivariate analysis (62H12) Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: This review traces the evolution of theory that started when Charles Stein in 1955 [In Proc. 3rd Berkeley Sympos. Math. Statist. Probab. I (1956) 197--206, Univ. California Press] showed that using each separate sample mean from $kge3$ Normal populations to estimate its own population mean $m{u}_i$ can be improved upon uniformly for every possible $mu=(m{u}_1,\mathrm{...},m{u}_k{)}^{\prime }$. The dominating estimators, referred to here as being "Model-I minimax," can be found by shrinking the sample means toward any constant vector. Admissible minimax shrinkage estimators were derived by Stein and others as posterior means based on a random effects model, "Model-II" here, wherein the $m{u}_i$ values have their own distributions. Section 2 centers on Figure 2, which organizes a wide class of priors on the unknown Level-II hyperparameters that have been proved to yield admissible Model-I minimax shrinkage estimators in the "equal variance case." Putting a flat prior on the Level-II variance is unique in this class for its scale-invariance and for its conjugacy, and it induces Stein's harmonic prior (SHP) on $m{u}_i$.

Recommendations

• Minimax multiple shrinkage estimation
• Shrinkage estimation in the two-way multivariate normal model
• Subjective hierarchical Bayes estimation of a multivariate normal mean: On the frequentist interface
• Publication:3212116
• A minimum average risk approach to shrinkage estimators of the normal mean

Cites work

• Admissible minimax estimation of a multivariate normal mean with arbitrary quadratic loss
• An adjusted maximum likelihood method for solving small area estimation problems
• Conjugate priors for exponential families
• Data Analysis Using Stein's Estimator and its Generalizations
• Estimating random effects via adjustment for density maximization
• Estimation of the mean of a multivariate normal distribution
• Estimation with quadratic loss.
• Families of minimax estimators of the mean of a multivariate normal distribution
• Hierarchical Poisson Regression Modeling
• scientific article; zbMATH DE number 3122730 (Why is no real title available?)
• scientific article; zbMATH DE number 4211273 (Why is no real title available?)
• scientific article; zbMATH DE number 3930141 (Why is no real title available?)
• scientific article; zbMATH DE number 3205757 (Why is no real title available?)
• scientific article; zbMATH DE number 3251903 (Why is no real title available?)
• scientific article; zbMATH DE number 3312335 (Why is no real title available?)
• Natural exponential families with quadratic variance functions: Statistical theory
• On the Admissibility of Invariant Estimators of One or More Location Parameters
• Parametric Empirical Bayes Inference: Theory and Applications
• Proper Bayes Minimax Estimators of the Multivariate Normal Mean
• Statistical decision theory and Bayesian analysis. 2nd ed

Cited in

(13)

• Estimating random-intercept models on data streams
• An objective prior for hyperparameters in normal hierarchical models
• Prediction and calibration for multiple correlated variables
• Improved minimax estimation of a multivariate normal mean under heteroscedasticity
• Online estimation of individual-level effects using streaming shrinkage factors
• Shrinkage estimation of the regression parameters with multivariate normal errors
• Robust and Accurate Inference via a Mixture of Gaussian and Student’s t Errors
• Estimating random effects via adjustment for density maximization
• On SURE estimates in hierarchical models assuming heteroscedasticity for both levels of a two-level normal hierarchical model
• Data transforming augmentation for heteroscedastic models
• Posterior propriety for hierarchical models with log-likelihoods that have norm bounds
• The choice of prior distribution for a covariance matrix in multivariate meta-analysis: a simulation study
• Improved multivariate normal mean estimation with unknown covariance when \(p\) is greater than \(n\)

This page was built for publication: Shrinkage estimation in multilevel normal models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2634658)