English

On normal approximations to $U$-statistics

Probability 2009-12-14 v2

Abstract

Let X1,...,Xn{X_1,...,X_n} be i.i.d. random observations. Let S=L+T\mathbb{S}=\mathbb{L}+\mathbb{T} be a UU-statistic of order k2k\ge2 where L\mathbb{L} is a linear statistic having asymptotic normal distribution, and T\mathbb{T} is a stochastically smaller statistic. We show that the rate of convergence to normality for S\mathbb{S} can be simply expressed as the rate of convergence to normality for the linear part L\mathbb{L} plus a correction term, (varT)ln2(varT)(\operatorname {var}\mathbb{T})\ln^2(\operatorname {var}\mathbb{T}), under the condition ET2<{\mathbb{E}\mathbb{T}^2<\infty}. An optimal bound without this log\log factor is obtained under a lower moment assumption ETα<{\mathbb {E}|\mathbb{T}|^{\alpha}<\infty} for α<2{\alpha<2}. Some other related results are also obtained in the paper. Our results extend, refine and yield a number of related-known results in the literature.

Keywords

Cite

@article{arxiv.0903.3081,
  title  = {On normal approximations to $U$-statistics},
  author = {Vidmantas Bentkus and Bing-Yi Jing and Wang Zhou},
  journal= {arXiv preprint arXiv:0903.3081},
  year   = {2009}
}

Comments

Published in at http://dx.doi.org/10.1214/09-AOP474 the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)

R2 v1 2026-06-21T12:41:50.987Z