Flexible results for quadratic forms with applications to variance components estimation

DOI10.1214/16-AOS1456MaRDI QIDQ524465zbMATH OpenOpenAlexFDO

Authors Lee H. Dicker, Murat A. Erdogdu

Publication date 2 May 2017

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

Full work available at URL https://arxiv.org/abs/1509.04388, https://projecteuclid.org/euclid.aos/1487667627

zbMATH Keywords

model misspecificationrandom-effects modelsStein's methodHanson-Wright inequalityuniform concentration bounds

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Central limit and other weak theorems (60F05) Approximations to statistical distributions (nonasymptotic) (62E17)

Abstract: We derive convenient uniform concentration bounds and finite sample multivariate normal approximation results for quadratic forms, then describe some applications involving variance components estimation in linear random-effects models. Random-effects models and variance components estimation are classical topics in statistics, with a corresponding well-established asymptotic theory. However, our finite sample results for quadratic forms provide additional flexibility for easily analyzing random-effects models in non-standard settings, which are becoming more important in modern applications (e.g. genomics). For instance, in addition to deriving novel non-asymptotic bounds for variance components estimators in classical linear random-effects models, we provide a concentration bound for variance components estimators in linear models with correlated random-effects. Our general concentration bound is a uniform version of the Hanson-Wright inequality. The main normal approximation result in the paper is derived using Reinert and R"{o}llin's (2009) embedding technique and multivariate Stein's method with exchangeable pairs.

Recommendations

• Variance inequalities for quadratic forms with applications
• A note on the Hanson-Wright inequality for random vectors with dependencies
• The covariances of quadratic forms of random variables and their applications in linear mixed models
• The lower tail of random quadratic forms with applications to ordinary least squares
• Eigenvalue distributions of variance components estimators in high-dimensional random effects models

Cited in

(13)

• Distributed Bayesian Inference in Linear Mixed-Effects Models
• Local Whittle estimation of high-dimensional long-run variance and precision matrices
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Some notes on concentration for \(\alpha\)-subexponential random variables
• Hanson-Wright inequality in Banach spaces
• On variance function estimation with quadratic forms
• Empirical Bayes estimates for a two-way cross-classified model
• High-dimensional linear models: a random matrix perspective
• Moderate-Dimensional Inferences on Quadratic Functionals in Ordinary Least Squares
• A Bayesian-motivated test for high-dimensional linear regression models with fixed design matrix
• Bounds for the chi-square approximation of Friedman's statistic by Stein's method
• scientific article; zbMATH DE number 5260825 (Why is no real title available?)
• WONDER: weighted one-shot distributed ridge regression in high dimensions

This page was built for publication: Flexible results for quadratic forms with applications to variance components estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q524465)