Large-dimensional Central Limit Theorem with Fourth-moment Error Bounds on Convex Sets and Balls
Probability
2021-03-03 v2 Statistics Theory
Statistics Theory
Abstract
We prove the large-dimensional Gaussian approximation of a sum of independent random vectors in together with fourth-moment error bounds on convex sets and Euclidean balls. We show that compared with classical third-moment bounds, our bounds have near-optimal dependence on and can achieve improved dependence on the dimension . For centered balls, we obtain an additional error bound that has a sub-optimal dependence on , but recovers the known result of the validity of the Gaussian approximation if and only if . We discuss an application to the bootstrap. We prove our main results using Stein's method.
Cite
@article{arxiv.2009.00339,
title = {Large-dimensional Central Limit Theorem with Fourth-moment Error Bounds on Convex Sets and Balls},
author = {Xiao Fang and Yuta Koike},
journal= {arXiv preprint arXiv:2009.00339},
year = {2021}
}
Comments
42 pages. We corrected a mistake in v1. Now the d=o(n) rate is proved only for centered balls