Asymptotic Joint Distribution of Extreme Eigenvalues of the Sample Covariance Matrix in the Spiked Population Model

preprint2012arXivOpen access

Abstract

In this paper, we consider a data matrix X∈CN×MX\in\mathbb{C}^{N\times M} where all the columns are i.i.d. samples being NN dimensional complex Gaussian of mean zero and covariance Σ∈CN×NΣ\in\mathbb{C}^{N\times N}. Here the population matrix ΣΣ is of finite rank perturbation of the identity matrix. This is the "spiked population model" first proposed by Johnstone in \cite{21}. As M,N→∞M, N\to\infty but M/N=γ∈(1,∞)M/N = γ\in(1, \infty), we first establish in this paper the asymptotic distribution of the smallest eigenvalue of the sample covariance matrix S:=XX∗/MS:= XX^*/M. It also exhibits a phase transition phenomenon proposed in \cite{1} --- the local fluctuation will be the generalized Tracy-Widom or the generalized Gaussian to be defined in the paper. Moreover we prove that the largest and the smallest eigenvalue are asymptotically independent as M,N→∞M, N\to\infty.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.