Spatial sign correlation

Alexander Dürre; Daniel Vogel; Roland Fried

doi:10.1016/j.jmva.2014.12.002

Spatial sign correlation

Alexander Dürre (Corresponding Author), Daniel Vogel, Roland Fried

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

6 Downloads (Pure)

Abstract

A new robust correlation estimator based on the spatial sign covariance matrix (SSCM) is proposed. We derive its asymptotic distribution and influence function at elliptical distributions. Finite sample and robustness properties are studied and compared to other robust correlation estimators by means of numerical simulations.

Original language	English
Pages (from-to)	89-105
Number of pages	17
Journal	Journal of Multivariate Analysis
Volume	135
Early online date	16 Dec 2014
DOIs	https://doi.org/10.1016/j.jmva.2014.12.002
Publication status	Published - Mar 2015

Keywords

stat.ME
62H12, 62G05, 62G35
elliptical distribution
Gaussian rank correlation
Gnanadesikan–Kettenring estimator
Kendall’s tau
spatial median
spatial sign covariance matrix
Spearman's rho

Access to Document

10.1016/j.jmva.2014.12.002Licence: Unspecified

Spatial Sign Correlation
NOTICE: this is the author’s version of a work that was accepted for publication in Journal of Multivariate Analysis. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Journal of Multivariate Analysis, VOL 135, 2015 DOI: 10.1016/j.jmva.2014.12.002
Submitted manuscript, 594 KB

http://arxiv.org/abs/1403.7635

Cite this

@article{90eb38ee59154b879123f5102a6a239b,

title = "Spatial sign correlation",

abstract = "A new robust correlation estimator based on the spatial sign covariance matrix (SSCM) is proposed. We derive its asymptotic distribution and influence function at elliptical distributions. Finite sample and robustness properties are studied and compared to other robust correlation estimators by means of numerical simulations.",

keywords = "stat.ME, 62H12, 62G05, 62G35, elliptical distribution, Gaussian rank correlation, Gnanadesikan–Kettenring estimator, Kendall{\textquoteright}s tau, spatial median, spatial sign covariance matrix, Spearman's rho",

author = "Alexander D{\"u}rre and Daniel Vogel and Roland Fried",

note = "20 pages, 7 figures, 2 tables",

year = "2015",

month = mar,

doi = "10.1016/j.jmva.2014.12.002",

language = "English",

volume = "135",

pages = "89--105",

journal = "Journal of Multivariate Analysis",

issn = "0047-259X",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Spatial sign correlation

AU - Dürre, Alexander

AU - Vogel, Daniel

AU - Fried, Roland

N1 - 20 pages, 7 figures, 2 tables

PY - 2015/3

Y1 - 2015/3

N2 - A new robust correlation estimator based on the spatial sign covariance matrix (SSCM) is proposed. We derive its asymptotic distribution and influence function at elliptical distributions. Finite sample and robustness properties are studied and compared to other robust correlation estimators by means of numerical simulations.

AB - A new robust correlation estimator based on the spatial sign covariance matrix (SSCM) is proposed. We derive its asymptotic distribution and influence function at elliptical distributions. Finite sample and robustness properties are studied and compared to other robust correlation estimators by means of numerical simulations.

KW - stat.ME

KW - 62H12, 62G05, 62G35

KW - elliptical distribution

KW - Gaussian rank correlation

KW - Gnanadesikan–Kettenring estimator

KW - Kendall’s tau

KW - spatial median

KW - spatial sign covariance matrix

KW - Spearman's rho

U2 - 10.1016/j.jmva.2014.12.002

DO - 10.1016/j.jmva.2014.12.002

M3 - Article

VL - 135

SP - 89

EP - 105

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

ER -

Spatial sign correlation

Abstract

Keywords

Access to Document

Fingerprint

Cite this