English

On the overestimation of the largest eigenvalue of a covariance matrix

Probability 2017-08-14 v1 Statistics Theory Mathematical Finance Statistics Theory

Abstract

In this paper, we use a new approach to prove that the largest eigenvalue of the sample covariance matrix of a normally distributed vector is bigger than the true largest eigenvalue with probability 1 when the dimension is infinite. We prove a similar result for the smallest eigenvalue.

Keywords

Cite

@article{arxiv.1708.03551,
  title  = {On the overestimation of the largest eigenvalue of a covariance matrix},
  author = {Soufiane Hayou},
  journal= {arXiv preprint arXiv:1708.03551},
  year   = {2017}
}

Comments

15 pages, 1 figure