Rates of multivariate normal approximation for statistics in geometric probability

DOI10.1214/22-AAP1822MaRDI QIDQ6103976zbMATH OpenOpenAlexFDO

Authors Matthias Schulte, J. E. Yukich

Publication date 5 June 2023

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2103.00625

zbMATH Keywords

multivariate normal approximationmultivariate statistics in geometric probabilityrandom Euclidean graphsstabilizationstochastic geometry

Mathematics Subject Classification ID

Geometric probability and stochastic geometry (60D05) Central limit and other weak theorems (60F05)

Abstract: We employ stabilization methods and second order Poincar'e inequalities to establish rates of multivariate normal convergence for a large class of vectors $(H_s^{(1)},\mathrm{...},H_s^{(m)})$, $sgeq1$, of statistics of marked Poisson processes on $mathbb{R}^d$, $dgeq2$, as the intensity parameter $s$ tends to infinity. Our results are applicable whenever the constituent functionals $H_s^{(i)}$, $iin1,\mathrm{...},m$, are expressible as sums of exponentially stabilizing score functions satisfying a moment condition. The rates are for the $d_2$-, $d_3$-, and $d_{convex}$-distances. When we compare with a centered Gaussian random vector, whose covariance matrix is given by the asymptotic covariances, the rates are in general unimprovable and are governed by the rate of convergence of $s^{-1}mCov(H_s^{(i)},H_s^{(j)})$, $i,jin1,\mathrm{...},m$, to the limiting covariance, shown to be of order $s^{-1/d}$. We use the general results to deduce rates of multivariate normal convergence for statistics arising in random graphs and topological data analysis as well as for multivariate statistics used to test equality of distributions. Some of our results hold for stabilizing functionals of Poisson input on suitable metric spaces.

Review text

The authors use stabilization methods and second-order Poincaré inequalities to obtain quantitative central limit theorems for multivariate functionals of Poisson point processes with large intensities. The functional of interest are expressed as sums of score functions which are exponentially stabilizing and satisfy a suitable moment condition. The rates are given in several metrics between multivariate distributions and are shown to be optimal. The obtained general results are applied to deduce rates of multivariate normal convergence for statistics arising in random graphs and topological data analysis as well as for multivariate statistics used to test the equality of distributions.

Recommendations

• Multivariate normal approximation in geometric probability
• Statistical rates on the multivariate approximation theory
• scientific article; zbMATH DE number 6130551
• Approximation rates for multivariate exceedances
• Approximations to Multivariate Normal Rectangle Probabilities Based on Conditional Expectations
• Multivariate normal approximation for functionals of random polytopes
• Asymptotic approximations for multivariate integrals with an application to multinormal probabilities

Cites work

• A class of Rényi information estimators for multidimensional densities
• A multivariate CLT for bounded decomposable random vectors with the best known rate
• A multivariate CLT for local dependence with \(n^{-1/2}\log n\) rate and applications to multivariate graph related statistics
• A multivariate two-sample test based on the number of nearest neighbor type coincidences
• Asymptotics for Euclidean functionals with power-weighted edges
• Central limit theorems for some graphs in computational geometry.
• Gaussian limits for random geometric measures
• Gaussian limits for random measures in geometric probability
• scientific article; zbMATH DE number 5722219 (Why is no real title available?)
• scientific article; zbMATH DE number 5209739 (Why is no real title available?)
• Limit theory for point processes in manifolds
• Limit theory for the Gilbert graph
• Multi-dimensional Gaussian fluctuations on the Poisson space
• Multivariate central limit theorems for random simplicial complexes
• Multivariate normal approximation in geometric probability
• Multivariate normal approximation with Stein's method of exchangeable pairs under a general linearity condition
• Multivariate normal approximations by Stein's method and size bias couplings
• Multivariate second order Poincaré inequalities for Poisson functionals
• Multivariate Two-Sample Tests Based on Nearest Neighbors
• New Berry-Esseen bounds for functionals of binomial point processes
• Normal Approximation by Stein’s Method
• Normal approximation for random sums
• Normal approximation for stabilizing functionals
• Normal approximation on Poisson spaces: Mehler's formula, second order Poincaré inequalities and stabilization
• On the rate of convergence in the multivariate CLT
• Probability theory of classical Euclidean optimization problems
• Quantitative two-scale stabilization on the Poisson space
• Random Geometric Graphs
• Rates of convergence for multivariate normal approximation with applications to dense graphs and doubly indexed permutation statistics
• Second-order properties and central limit theorems for geometric functionals of Boolean models
• The topology of probability distributions on manifolds
• Weak laws of large numbers in geometric probability

Cited in

(13)

• Normal approximation for stabilizing functionals
• Approximation rates for multivariate exceedances
• Gaussian approximation for sums of region-stabilizing scores
• Quantitative two-scale stabilization on the Poisson space
• Multivariate second order Poincaré inequalities for Poisson functionals
• Multivariate normal approximation in geometric probability
• Multivariate central limit theorems for Rademacher functionals with applications
• Normal approximation in total variation for statistics in geometric probability
• On the rate of normal approximation for Poisson continuum percolation
• A flexible approach for normal approximation of geometric and topological statistics
• Quantitative CLTs on the Poisson space via Skorohod estimates and p-Poincaré inequalities
• Normal approximation on Poisson spaces: Mehler's formula, second order Poincaré inequalities and stabilization
• Rates of convergence for multivariate normal approximation with applications to dense graphs and doubly indexed permutation statistics

This page was built for publication: Rates of multivariate normal approximation for statistics in geometric probability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6103976)