Determining the signal dimension in second order source separation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Virta, Joni, Nordhausen, Klaus
Format: Preprint
Published: 2018
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910405486444544
author Virta, Joni
Nordhausen, Klaus
author_facet Virta, Joni
Nordhausen, Klaus
contents While an important topic in practice, the estimation of the number of non-noise components in blind source separation has received little attention in the literature. Recently, two bootstrap-based techniques for estimating the dimension were proposed, and although very efficient, they suffer from the long computation times caused by the resampling. We approach the problem from a large sample viewpoint and develop an asymptotic test for the true dimension. Our test statistic based on second-order temporal information has a very simple limiting distribution under the null hypothesis and requires no parameters to estimate. Comparisons to the resampling-based estimates show that the asymptotic test provides comparable error rates with significantly faster computation time. An application to sound recording data is used to illustrate the method in practice.
format Preprint
id arxiv_https___arxiv_org_abs_1808_10669
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle Determining the signal dimension in second order source separation
Virta, Joni
Nordhausen, Klaus
Statistics Theory
While an important topic in practice, the estimation of the number of non-noise components in blind source separation has received little attention in the literature. Recently, two bootstrap-based techniques for estimating the dimension were proposed, and although very efficient, they suffer from the long computation times caused by the resampling. We approach the problem from a large sample viewpoint and develop an asymptotic test for the true dimension. Our test statistic based on second-order temporal information has a very simple limiting distribution under the null hypothesis and requires no parameters to estimate. Comparisons to the resampling-based estimates show that the asymptotic test provides comparable error rates with significantly faster computation time. An application to sound recording data is used to illustrate the method in practice.
title Determining the signal dimension in second order source separation
topic Statistics Theory
url https://arxiv.org/abs/1808.10669