Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles
Statistics Theory
2022-03-08 v3 Probability
Statistics Theory
Abstract
Let be independent centered random vectors in . This paper shows that, even when may grow with , the probability can be approximated by its Gaussian analog uniformly in hyperrectangles in as under appropriate moment assumptions, as long as . This improves a result of Chernozhukov, Chetverikov & Kato [Ann. Probab. 45 (2017) 2309-2353] in terms of the dimension growth condition. When has a common factor across the components, this condition can be further improved to . The corresponding bootstrap approximation results are also developed. These results serve as a theoretical foundation of simultaneous inference for high-dimensional models.
Cite
@article{arxiv.1911.00160,
title = {Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles},
author = {Yuta Koike},
journal= {arXiv preprint arXiv:1911.00160},
year = {2022}
}
Comments
33 pages. The constant of Lemma 2.2 is modified and the proof is corrected