First-order covariance inequalities via Stein's method

DOI10.3150/19-BEJ1182zbMATH Open1457.60035arXiv1906.08372OpenAlexW3003272030MaRDI QIDQ2174992FDOQ2174992

Authors: Marie Ernst, Yvik Swan, Gesine Reinert 

Publication date: 27 April 2020

Published in: Bernoulli (Search for Journal in Brave)

Abstract: We propose probabilistic representations for inverse Stein operators (i.e. solutions to Stein equations) under general conditions; in particular we deduce new simple expressions for the Stein kernel. These representations allow to deduce uniform and non-uniform Stein factors (i.e. bounds on solutions to Stein equations) and lead to new covariance identities expressing the covariance between arbitrary functionals of an arbitrary {univariate} target in terms of a weighted covariance of the derivatives of the functionals. Our weights are explicit, easily computable in most cases, and expressed in terms of objects familiar within the context of Stein's method. Applications of the Cauchy-Schwarz inequality to these weighted covariance identities lead to sharp upper and lower covariance bounds and, in particular, weighted Poincar'e inequalities. Many examples are given and, in particular, classical variance bounds due to Klaassen, Brascamp and Lieb or Otto and Menz are corollaries. Connections with more recent literature are also detailed.

Full work available at URL: https://arxiv.org/abs/1906.08372

Recommendations

• A theoretical study of Stein's covariance estimator
• How a probabilistic analogue of the mean value theorem yields stein-type covariance identities
• Estimation of a covariance matrix under Stein's loss
• Stein's method for concentration inequalities
• An extended Stein-type covariance identity for the Pearson family with applications to lower variance bounds
• An inequality for covariance with applications
• Covariance inequalities
• Improved estimation of the covariance matrix under Stein's loss
• An inequality for the variance of the first order statistic
• On Stein's method for multivariate self-decomposable laws with finite first moment

zbMATH Keywords

Stein equation[https://portal.mardi4nfdi.de/w/index.php?title=+Special%3ASearch&search=Cram%EF%BF%BD%EF%BF%BDr-Rao+inequality&go=Go Cram��r-Rao inequality]variance boundsStein kernelcovariance identities

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Central limit and other weak theorems (60F05)

Cites Work

• Mills' ratio: Monotonicity patterns and functional inequalities
• Binomial approximation to the Poisson binomial distribution
• Distributional transformations, orthogonal polynomials, and Stein characterizations
• Normal Approximation by Stein’s Method
• Stein's density approach and information inequalities
• Normal approximations with Malliavin calculus. From Stein's method to universality
• Continuity of Solutions of Parabolic and Elliptic Equations
• Title not available (Why is that?)
• Fundamentals of Stein's method
• Title not available (Why is that?)
• On the covariance between functions
• Parametric Stein operators and variance bounds
• Title not available (Why is that?)
• Stein's method for invariant measures of diffusions via Malliavin calculus
• An extended Stein-type covariance identity for the Pearson family with applications to lower variance bounds
• A natural derivative on [0, n] and a binomial Poincaré inequality
• Nonnormal approximation by Stein's method of exchangeable pairs with application to the Curie-Weiss model
• Stein's method for the beta distribution and the Pólya-Eggenberger urn
• On extensions of the Brunn-Minkowski and Prekopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equation
• Poincaré-type inequalities for stable densities
• On an inequality of Chernoff
• The identification of an element of a large population in the presence of noise
• An inequality for the multivariate normal distribution
• On upper and lower bounds for the variance of a function of a random variable
• Poisson approximation for dependent trials
• Closed form summation for classical distributions: variations on a theme of de Moivre
• A generalization of covariance identity and related characterizations
• Some Stein-type inequalities for multivariate elliptical distributions and applications
• On an Inequality and a Related Characterization of the Normal Distribution
• On upper bounds for the variance of functions of random variables
• Uniform logarithmic Sobolev inequalities for conservative spin systems with super-quadratic single-site potential
• A short survey of Stein's method
• Title not available (Why is that?)
• Characterizations of distributions by variance bounds
• Lower variance bounds and a new proof of the central limit theorem
• Multivariate Stein factors for a class of strongly log-concave distributions
• A note on Stein's lemma for multivariate elliptical distributions
• On characterizations of distributions by mean absolute deviation and variance bounds
• A characterization of the Pearson system of distributions and the associated orthogonal polynomials
• Unified extension of variance bounds for integrated Pearson family
• Matrix variance inequalities for multivariate distributions
• Orthogonal polynomials in Stein's method
• Bounds for the variance of functions of random variables by orthogonal polynomials and Bhattacharya bounds
• First-order covariance inequalities via Stein's method
• The discrete mohr and noll inequality with applications to variance bounds
• Intertwining relations for one-dimensional diffusions and application to functional inequalities
• Asymmetric covariance estimates of Brascamp-Lieb type and related inequalities for log-concave measures
• Poincaré-type inequalities via stochastic integrals
• Stein's method for comparison of univariate distributions
• Distances between nested densities and a measure of the impact of the prior in Bayesian statistics
• Stein's method of exchangeable pairs for the Beta distribution and generalizations
• The collected works of Wassily Hoeffding. Ed. by N. I. Fisher and P. K. Sen
• Variance inequalities for covariance kernels and applications to central limit theorems
• Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
• On Stein's Method for Infinitely Divisible Laws with Finite First Moment
• Approximation of stable law in Wasserstein-1 distance by Stein's method
• Title not available (Why is that?)
• On Stein operators for discrete approximations
• Existence of Stein kernels under a spectral gap, and discrepancy bounds
• Stein kernels and moment maps
• Fokker–Planck equations in the modeling of socio-economic phenomena
• Title not available (Why is that?)
• Measuring sample quality with diffusions
• Orthogonal polynomials in the cumulative Ord family and its application to variance bounds
• Multivariate approximation in total variation. II: Discrete normal approximation
• Efron's monotonicity property for measures on \(\mathbb{R}^2\)
• A weak law of large numbers for empirical measures via Stein's method
• Poincaré inequalities on intervals -- application to sensitivity analysis
• A note on spectral gap and weighted Poincaré inequalities for some one-dimensional diffusions
• Stein's method for asymmetric \(\alpha \)-stable distributions, with application to the stable CLT
• On the isoperimetric constant, covariance inequalities and \(L_{p}\)-Poincaré inequalities in dimension one
• On Stein's method for multivariate self-decomposable laws
• Higher-order Stein kernels for Gaussian approximation
• Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one
• A note on a variance bound for the multinomial and the negative multinomial distribution
• On infinite covariance expansions

Cited In (17)

• On probabilistic mean value theorem and covariance identities
• Distances between distributions via Stein's method
• An extended Stein-type covariance identity for the Pearson family with applications to lower variance bounds
• Some inequalities for covariance with applications in statistics
• How a probabilistic analogue of the mean value theorem yields stein-type covariance identities
• On infinite covariance expansions
• Stein’s method and approximating the multidimensional quantum harmonic oscillator
• General Stein-Type Covariance Decompositions with Applications to Insurance and Finance
• On Brascamp-Lieb and Poincaré type inequalities for generalized tempered stable distribution
• Rates of Fisher information convergence in the central limit theorem for nonlinear statistics
• Bounding the \(L^1\)-distance between one-dimensional continuous and discrete distributions via Stein's method
• First-order covariance inequalities via Stein's method
• New error bounds for Laplace approximationviaStein’s method
• A note on one-dimensional Poincaré inequalities by Stein-type integration
• Title not available (Why is that?)
• Stein's density method for multivariate continuous distributions
• Stein's density approach and information inequalities

This page was built for publication: First-order covariance inequalities via Stein's method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2174992)