Optimal-order bounds on the rate of convergence to normality in the multivariate delta method

DOI10.1214/16-EJS1133MaRDI QIDQ276236zbMATH OpenOpenAlexFDO

Authors Iosif Pinelis, Raymond Molzon

Publication date 3 May 2016

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

Full work available at URL https://arxiv.org/abs/0906.0177, https://projecteuclid.org/euclid.ejs/1460463653

zbMATH Keywords

Berry-Esseen boundsconvergence ratesmaximum likelihood estimatorsexponential inequalitiessphericity testcanonical correlationdelta methodnoncentral Hotelling statisticnoncentral student statisticnonlinear statisticsPearson's correlation coefficientCramér's tilt

Mathematics Subject Classification ID

Characteristic functions; other transforms (60E10) Parametric hypothesis testing (62F03) Asymptotic properties of parametric estimators (62F12) Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20) Asymptotic properties of parametric tests (62F05) Inequalities; stochastic orderings (60E15) Central limit and other weak theorems (60F05)

Abstract: Uniform and nonuniform Berry--Esseen (BE) bounds of optimal orders on the closeness to normality for general abstract nonlinear statistics are given, which are then used to obtain optimal bounds on the rate of convergence in the delta method for vector statistics. Specific applications to Pearson's, non-central Student's and Hotelling's statistics, sphericity test statistics, a regularized canonical correlation, and maximum likelihood estimators (MLEs) are given; all these uniform and nonuniform BE bounds appear to be the first known results of these kinds, except for uniform BE bounds for MLEs. When applied to the well-studied case of the central Student statistic, our general results compare well with known ones in that case, obtained previously by specialized methods. The proofs use a Stein-type method developed by Chen and Shao, a Cram'er-type of tilt transform, exponential and Rosenthal-type inequalities for sums of random vectors established by Pinelis, Sakhanenko, and Utev, as well as a number of other, quite recent results motivated by this study. The method allows one to obtain bounds with explicit and rather moderate-size constants, at least as far as the uniform bounds are concerned. For instance, one has the uniform BE bound $3.61mathbbE(Y_1^6+Z_1^6),(1+sigm{a}^{-3})/sqrtn$ for the Pearson sample correlation coefficient based on independent identically distributed random pairs $(Y_1,Z_1),dots,(Y_n,Z_n)$ with $mathbbE{Y}_1=mathbbE{Z}_1=mathbbE{Y}_1{Z}_1=0$ and $mathbbE{Y}_1^2=mathbbE{Z}_1^2=1$, where $sigma:=sqrtmathbbE{Y}_1^2{Z}_1^2$.

Recommendations

• The rate of convergence for multivariate sampling statistics
• Berry-Esseen bounds for statistics of weakly dependent samples
• Optimal-order uniform and nonuniform bounds on the rate of convergence to normality for maximum likelihood estimators
• Berry-Esseen bounds for von Mises and \(U\)-statistics
• scientific article; zbMATH DE number 3936187

Cites work

• scientific article; zbMATH DE number 3886886 (Why is no real title available?)
• scientific article; zbMATH DE number 3504209 (Why is no real title available?)
• scientific article; zbMATH DE number 3347500 (Why is no real title available?)
• A Berry-Esséen bound for Student's statistic in the non-i. i. d. case
• A class of Wasserstein metrics for probability distributions
• A new test for sphericity of the covariance matrix for high dimensional data
• Application of a delta-method for random operators to testing equality of two covariance operators
• Berry-Esseen bounds for estimating undirected graphs
• Bounds for the asymptotic normality of the maximum likelihood estimator using the Delta method
• Bounds for the normal approximation of the maximum likelihood estimator
• Canonical correlation for stochastic processes
• Exact Exponential Bounds for Sums of Independent Random Variables
• Exact Rosenthal-type bounds
• Exact convergence rate and leading term in central limit theorem for Student's \(t\) statistic.
• Exact lower bounds on the exponential moments of truncated random variables
• Expansions and Asymptotics for Statistics
• Infinitely divisible probability measures and the converse Kolmogorov inequality in Banach spaces
• Integrability of Infinite Sums of Independent Vector-Valued Random Variables
• Introduction to empirical processes and semiparametric inference
• Limit laws of the empirical Wasserstein distance: Gaussian distributions
• Limiting distributions of the non-central \(t\)-statistic and their applications to the power of \(t\)-tests under non-normality
• Matrix Analysis
• Methods of canonical analysis for functional data.
• Normal approximation for nonlinear statistics using a concentration inequality approach
• On a Theorem of Pitman
• On smoothness conditions and convergence rates in the CLT in Banach spaces
• On some test criteria for covariance matrix
• On the Accuracy of Normal Approximation in Banach Spaces
• On the Bennett-Hoeffding inequality
• On the constant in the nonuniform version of the Berry-Ess�en theorem
• On the rate of convergence in the central limit theorem in Banach spaces
• On the rate of convergence in the multivariate CLT
• On the subspaces of \(L^p\) \((p > 2)\) spanned by sequences of independent random variables
• On the validity of the formal Edgeworth expansion
• Optimal re-centering bounds, with applications to Rosenthal-type concentration of measure inequalities
• Optimal-order bounds on the rate of convergence to normality in the multivariate delta method
• Perturbation bounds and truncations for a class of Markovian queues
• Perturbation theory for linear operators.
• Probability Inequalities for Sums of Bounded Random Variables
• Probability Inequalities for the Sum of Independent Random Variables
• Quasi-likelihood and its application. A general approach to optimal parameter estimation
• Remarks on Inequalities for Large Deviation Probabilities
• Rosenthal-Type Inequalities for Martingales in 2-Smooth Banach Spaces
• Second-order asymptotics for quantum hypothesis testing
• Self-normalized limit theorems: a survey
• Some hypothesis tests for the covariance matrix when the dimension is large compared to the sample size
• Some properties of canonical correlations and variates in infinite dimensions
• Statistical inference for Sobol pick-freeze Monte Carlo method
• Tempered stable distributions and processes
• Tests for high-dimensional covariance matrices
• The Accuracy of Gaussian Approximation in Banach Spaces
• The Berry-Esseen bound for Student's statistic
• The Berry-Esseen bound for minimum contrast estimates
• The Frechet distance between multivariate normal distributions
• The Fréchet derivative of an analytic function of a bounded operator with some applications
• The accuracy of the normal approximation for estimates of vector parameters
• The delta method for analytic functions of random operators with application to functional data
• The distance between two random vectors wigh given dispersion matrices
• The law of large numbers and the central limit theorem in Banach spaces
• The rate of convergence for multivariate sampling statistics
• When is the Student \(t\)-statistic asymptotically standard normal?

Cited in

(17)

• Exact Bounds on the Truncated-Tilted Mean, with Applications
• The rate of convergence for multivariate sampling statistics
• On principal components regression with Hilbertian predictors
• Assessing the multivariate normal approximation of the maximum likelihood estimator from high-dimensional, heterogeneous data
• Stein's method for functions of multivariate normal random variables
• Explicit non-asymptotic bounds for the distance to the first-order Edgeworth expansion
• Multivariate normal approximation of the maximum likelihood estimator via the delta method
• Wasserstein distance error bounds for the multivariate normal approximation of the maximum likelihood estimator
• Uniformity and the delta method
• Optimal-order bounds on the rate of convergence to normality in the multivariate delta method
• An asymptotically optimal transform of Pearson's correlation statistic
• Bootstrapping and sample splitting for high-dimensional, assumption-lean inference
• Infinite volume Gibbs states and metastates of the random field mean-field spherical model
• Bounds in \(L^1\) Wasserstein distance on the normal approximation of general M-estimators
• Bounds for the normal approximation of the maximum likelihood estimator from \(m\)-dependent random variables
• On the \(T\)-test
• On universally consistent and fully distribution-free rank tests of vector independence

This page was built for publication: Optimal-order bounds on the rate of convergence to normality in the multivariate delta method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q276236)