Gaussian Approximations for the $k$th coordinate of sums of random vectors

TL;DR

This paper develops Gaussian approximation methods for the th coordinate of sums of high-dimensional random vectors, extending previous work from maxima to general coordinates and large dimensions.

Contribution

It introduces new Gaussian approximation bounds, justifies Gaussian multiplier bootstrap for general , and extends results to diverging  and sums of top coordinates.

Findings

Gaussian approximation bounds for the th coordinate

Validation of Gaussian multiplier bootstrap for general 

Extension to diverging  and sums of top coordinates

Abstract

We consider the problem of Gaussian approximation for the $\kappa$th coordinate of a sum of high-dimensional random vectors. Such a problem has been studied previously for $\kappa=1$ (i.e., maxima). However, in many applications, a general $\kappa\geq1$ is of great interest, which is addressed in this paper. We make four contributions: 1) we first show that the distribution of the $\kappa$th coordinate of a sum of random vectors, $\boldsymbol{X}= (X_{1},\cdots,X_{p})^{\sf T}= n^{-1/2}\sum_{i=1}^n \boldsymbol{x}_{i}$, can be approximated by that of Gaussian random vectors and derive their Kolmogorov's distributional difference bound; 2) we provide the theoretical justification for estimating the distribution of the $\kappa$th coordinate of a sum of random vectors using a Gaussian multiplier procedure, which multiplies the original vectors with i.i.d. standard Gaussian random variables; 3) we extend the Gaussian approximation result and Gaussian multiplier bootstrap procedure to a more general case where $\kappa$ diverges; 4) we further consider the Gaussian approximation for a square sum of the first $d$ largest coordinates of $\boldsymbol{X}$. All these results allow the dimension $p$ of random vectors to be as large as or much larger than the sample size $n$.