Refereed journal article or data article (A1)
Asymptotic and Bootstrap Tests for the Dimension of the Non-Gaussian Subspace
List of Authors: Nordhausen K, Oja H, Tyler DE, Virta J
Publisher: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication year: 2017
Journal: IEEE Signal Processing Letters
Journal name in source: IEEE SIGNAL PROCESSING LETTERS
Journal acronym: IEEE SIGNAL PROC LET
Volume number: 24
Issue number: 6
Start page: 887
End page: 891
Number of pages: 5
ISSN: 1070-9908
eISSN: 1558-2361
DOI: http://dx.doi.org/10.1109/LSP.2017.2696880
Self-archived copy’s web address: https://arxiv.org/abs/1701.06836
Abstract
Dimension reduction is often a preliminary step in the analysis of large data sets. The so-called non-Gaussian component analysis searches for a projection onto the non-Gaussian part of the data, and it is then important to know the correct dimension of the non-Gaussian signal subspace. In this letter, we develop asymptotic as well as bootstrap tests for the dimension based on the popular fourth-order blind identification method.
Dimension reduction is often a preliminary step in the analysis of large data sets. The so-called non-Gaussian component analysis searches for a projection onto the non-Gaussian part of the data, and it is then important to know the correct dimension of the non-Gaussian signal subspace. In this letter, we develop asymptotic as well as bootstrap tests for the dimension based on the popular fourth-order blind identification method.
UTU Research Portal