Article (Scientific journals)
Multivariate coefficients of variation: Comparison and influence functions
Aerts, Stéphanie; Haesbroeck, Gentiane; Ruwet, Christel
2015In Journal of Multivariate Analysis, 142, p. 183-198
Peer Reviewed verified by ORBi
 

Files


Full Text
JMVA_MultivariateCV.pdf
Publisher postprint (726.74 kB)
Request a copy
Annexes
1. MultCV.zip
(15.06 kB)
Code R
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Coeffiicient of variation; Influence function; Minimum Covariance Determinant Estimator
Abstract :
[en] In the univariate setting, coefficients of variation are well-known and used to compare the variability of populations characterized by variables expressed in different units or having really different means. When dealing with more than one variable, the use of such a relative dispersion measure is much less common even though several generalizations of the coefficient of variation to the multivariate setting have been introduced in the literature. In this paper, the lack of robustness of the sample versions of the multivariate coefficients of variation (MCV) is illustrated by means of influence functions and some robust counterparts based either on the Minimum Covariance Determinant (MCD) estimator or on the S estimator are advocated. Then, focusing on two of the considered MCV’s, a diagnostic tool is derived and its efficiency in detecting observations having an unduly large effect on variability is illustrated on a real-life data set. The influence functions are also used to compute asymptotic variances under elliptical distributions, yielding approximate confidence intervals. Finally, simulations are conducted in order to compare, in a finite sample setting, the performance of the classical and robust MCV’s in terms of variability and in terms of coverage probability of the corresponding asymptotic confidence intervals.
Disciplines :
Mathematics
Author, co-author :
Aerts, Stéphanie ;  Université de Liège - ULiège > HEC-Ecole de gestion : UER > UER Opérations : Informatique de gestion
Haesbroeck, Gentiane ;  Université de Liège - ULiège > Département de mathématique > Statistique mathématique
Ruwet, Christel ;  Université de Liège - ULiège > Département de mathématique > Statistique mathématique
Language :
English
Title :
Multivariate coefficients of variation: Comparison and influence functions
Publication date :
December 2015
Journal title :
Journal of Multivariate Analysis
ISSN :
0047-259X
eISSN :
1095-7243
Publisher :
Academic Press
Volume :
142
Pages :
183-198
Peer reviewed :
Peer Reviewed verified by ORBi
Name of the research project :
Robust multivariate dispersion measures
Funders :
IAP Research Network P7/06 of the Belgian State.
Available on ORBi :
since 05 June 2014

Statistics


Number of views
197 (42 by ULiège)
Number of downloads
28 (12 by ULiège)

Scopus citations®
 
28
Scopus citations®
without self-citations
26
OpenCitations
 
27

Bibliography


Similar publications



Contact ORBi