Start Submission Become a Reviewer

Reading: Asymptotic Distribution of the Largest Eigenvalue via Geometric Representations of High-Dime...

Download

A- A+
dyslexia friendly

Articles

Asymptotic Distribution of the Largest Eigenvalue via Geometric Representations of High-Dimension, Low-Sample-Size Data

Authors:

Aki Ishii ,

Graduate School of Pure and Applied Sciences, University of Tsukuba, Ibaraki,, JP
X close

Kazuyoshi Yata,

Institute of Mathematics, University of Tsukuba, Ibaraki,, JP
X close

Makoto Aoshima

Institute of Mathematics, University of Tsukuba, Ibaraki,, JP
X close

Abstract

A common feature of high-dimensional data is that the data dimension is high, however, the sample size is relatively low. We call such a data HDLSS data. In this paper, we study HDLSS asymptotics for Gaussian-type HDLSS data. We find a surprising geometric representation of the HDLSS data in a dual space. We give an estimator of the eigenvalue by using the noise-reduction (NR) methodology. We show that the estimator enjoys consistency properties under mild conditions when the dimension is high. We provide an asymptotic distribution for the largest eigenvalue when the dimension is high while the sample size is fixed. We show that the estimator given by the NR methodology holds the asymptotic distribution under a condition milder than that for the conventional estimator.

DOI: http://dx.doi.org/10.4038/sljastats.v5i4.7785

How to Cite: Ishii, A., Yata, K. & Aoshima, M., (2014). Asymptotic Distribution of the Largest Eigenvalue via Geometric Representations of High-Dimension, Low-Sample-Size Data. Sri Lankan Journal of Applied Statistics. 5(4), pp.81–94. DOI: http://doi.org/10.4038/sljastats.v5i4.7785
Published on 14 Dec 2014.
Peer Reviewed

Downloads

  • PDF (EN)

    comments powered by Disqus