A new method of normal approximation

Abstract

We introduce a new version of Stein's method that reduces a large class of normal approximation problems to variance bounding exercises, thus making a connection between central limit theorems and concentration of measure. Unlike Skorokhod embeddings, the object whose variance must be bounded has an explicit formula that makes it possible to carry out the program more easily. As an application, we derive a general CLT for functions that are obtained as combinations of many local contributions, where the definition of "local" itself depends on the data. Several examples are given, including the solution to a nearest-neighbor CLT problem posed by P. Bickel.

Published in at http://dx.doi.org/10.1214/07-AOP370 the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (5)

• Normal approximation under local dependence
• Multivariate normal approximation using exchangeable pairs
• Stein's method and the zero bias transformation with application to simple random sampling
• Large deviation asymptotics for occupancy problems
• Fluctuations of eigenvalues and second order Poincaré inequalities

Cited by in corpus (57)

• Quantitative stochastic homogenization and large-scale regularity
• Multivariate normal approximation using exchangeable pairs
• The additive structure of elliptic homogenization
• New rates for exponential approximation and the theorems of Rényi and Yaglom
• Disorder chaos and multiple valleys in spin glasses
• A short survey of Stein's method
• Stein couplings for normal approximation
• On Stein's Method for Infinitely Divisible Laws With Finite First Moment
• Berry-Esseen Bounds of Normal and Non-normal Approximation for Unbounded Exchangeable Pairs
• From Stein identities to moderate deviations
• On the size of chaos via Glauber calculus in the classical mean-field dynamics
• Limit theory for point processes in manifolds
• Analyticity of homogenized coefficients under Bernoulli perturbations and the Clausius-Mossotti formulas
• Minimax Distribution Estimation in Wasserstein Distance
• Normal approximation for coverage models over binomial point processes
• A Central Limit Theorem for the Length of the Longest Common Subsequences in Random Words
• Central limit theorems via Stein's method for randomized experiments under interference
• Normal approximation and almost sure central limit theorem for non-symmetric Rademacher functionals
• A stroll along the gamma
• Cramér-type Moderate Deviation Theorems for Nonnormal Approximation
• Central limit theorems for patterns in multiset permutations and set partitions
• High-dimensional Central Limit Theorems by Stein's Method
• Minimal spanning trees and Stein's method
• A central limit theorem for the two-sided descent statistic on Coxeter groups
• Limit theorems for empirical Fréchet means of independent and non-identically distributed manifold-valued random variables
• New Kolmogorov bounds for functionals of binomial point processes
• A Central Limit Theorem for the Optimal Alignments Score in Multiple Random Words
• Fluctuations of eigenvalues and second order Poincaré inequalities
• Quantitative two-scale stabilization on the Poisson space
• Generalized kernel distance covariance in high dimensions: non-null CLTs and power universality
• Pure Nash Equilibria and Best-Response Dynamics in Random Games
• On Stein's Method for Multivariate Self-Decomposable Laws With Finite First Moment
• Berry-Esseen bounds and multivariate limit theorems for functionals of Rademacher sequences
• Normal approximation for the net flux through a random conductor
• Scaling limits of energies and correctors
• Fluctuations of Quadratic Chaos
• Poisson and normal approximations for the measurable functions of independent random variables
• Empirical bounds for functions with weak interactions
• Quantitative normal approximation for sums of random variables with multilevel local dependence structure
• Multiscale second-order Poincaré inequalities in probability
• Nourdin-Peccati analysis on Wiener and Wiener-Poisson space for general distributions
• Concentration of measures via size biased couplings
• Local limit theorems for occupancy models
• Bounds to the normal for proximity region graphs
• Skewness correction in tail probability approximations for sums of local statistics
• Causal Inference in Longitudinal Data under Unknown Interference
• Central limit theorem for linear spectral statistics of block-Wigner-type matrices
• Spin glasses and Stein's method
• A quantitative central limit theorem for the effective conductance on the discrete torus
• A central limit theorem for random disc-polygons in smooth convex discs
• Local central limit theorems in stochastic geometry
• Statistical tests based on Rényi entropy estimation
• Non-uniform Berry-Esseen Bound by Unbounded Exchangeable Pair Approach
• Random polytopes: central limit theorems for intrinsic volumes
• Stein's lemma, Malliavin calculus, and tail bounds, with application to polymer fluctuation exponent
• Extreme Values of Permutation Statistics
• Normal approximation for isolated balls in an urn allocation model