A CLT for the LSS of large dimensional sample covariance matrices with unbounded dispersions

TL;DR

This paper extends the central limit theorem for linear spectral statistics of large sample covariance matrices to cases with unbounded population covariances, enabling broader applications in high-dimensional statistics.

Contribution

It removes the boundedness restriction in the Bai-Silverstein theorem, allowing for unbounded and diverging spiked eigenvalues in the analysis.

Findings

The new CLT accommodates unbounded and diverging eigenvalues.

Simulation results validate the theoretical findings.

Asymptotic distributions for corrected tests are derived.

Abstract

In this paper, we establish the central limit theorem (CLT) for linear spectral statistics (LSS) of large-dimensional sample covariance matrix when the population covariance matrices are not uniformly bounded, which is a nontrivial extension of the Bai-Silverstein theorem (BST) (2004). The latter has strongly stimulated the development of high-dimensional statistics, especially the application of random matrix theory to statistics. However, the assumption of uniform boundedness of the population covariance matrices is found strongly limited to the applications of BST. The aim of this paper is to remove the blockages to the applications of BST. The new CLT, allows the spiked eigenvalues to exist and tend to infinity. It is interesting to note that the roles of either spiked eigenvalues or the bulk eigenvalues or both of the two are dominating in the CLT. Moreover, the results are checked by simulation studies with various population settings. The CLT for LSS is then applied for testing the hypothesis that a covariance matrix $ \bSi $ is equal to an identity matrix. For this, the asymptotic distributions for the corrected likelihood ratio test (LRT) and Nagao's trace test (NT) under alternative are derived, and we also propose the asymptotic power of LRT and NT under certain alternatives.