Shrinkage and spectral filtering of correlation matrices: a comparison via the Kullback-Leibler distance

Rosario Nunzio Mantegna, Michele Tumminello, Fabrizio Lillo, Fabrizio Lillo, Rosario N. Mantegna, Michele Tumminello

Risultato della ricerca: Article

12 Citazioni (Scopus)

Abstract

The problem of filtering information from large correlation matrices is of great importance in many applications. We have recently proposed the use of the Kullback-Leibler distance to measure the performance of filtering algorithms in recovering the underlying correlation matrix when the variables are described by a multivariate Gaussian distribution. Here we use the Kullback-Leibler distance to investigate the performance of filtering methods based on Random Matrix Theory and on the shrinkage technique. We also present some results on the application of the Kullback-Leibler distance to multivariate data which are non Gaussian distributed
Lingua originaleEnglish
pagine (da-a)4079-4088
Numero di pagine10
RivistaActa Physica Polonica B
Volume38
Stato di pubblicazionePublished - 2007

Fingerprint

shrinkage
matrix theory
normal density functions

All Science Journal Classification (ASJC) codes

  • Physics and Astronomy(all)

Cita questo

Shrinkage and spectral filtering of correlation matrices: a comparison via the Kullback-Leibler distance. / Mantegna, Rosario Nunzio; Tumminello, Michele; Lillo, Fabrizio; Lillo, Fabrizio; Mantegna, Rosario N.; Tumminello, Michele.

In: Acta Physica Polonica B, Vol. 38, 2007, pag. 4079-4088.

Risultato della ricerca: Article

@article{999dcf8a8627405289366c672b9ed743,
title = "Shrinkage and spectral filtering of correlation matrices: a comparison via the Kullback-Leibler distance",
abstract = "The problem of filtering information from large correlation matrices is of great importance in many applications. We have recently proposed the use of the Kullback-Leibler distance to measure the performance of filtering algorithms in recovering the underlying correlation matrix when the variables are described by a multivariate Gaussian distribution. Here we use the Kullback-Leibler distance to investigate the performance of filtering methods based on Random Matrix Theory and on the shrinkage technique. We also present some results on the application of the Kullback-Leibler distance to multivariate data which are non Gaussian distributed",
author = "Mantegna, {Rosario Nunzio} and Michele Tumminello and Fabrizio Lillo and Fabrizio Lillo and Mantegna, {Rosario N.} and Michele Tumminello",
year = "2007",
language = "English",
volume = "38",
pages = "4079--4088",
journal = "Acta Physica Polonica B",
issn = "0587-4254",
publisher = "Jagellonian University",

}

TY - JOUR

T1 - Shrinkage and spectral filtering of correlation matrices: a comparison via the Kullback-Leibler distance

AU - Mantegna, Rosario Nunzio

AU - Tumminello, Michele

AU - Lillo, Fabrizio

AU - Lillo, Fabrizio

AU - Mantegna, Rosario N.

AU - Tumminello, Michele

PY - 2007

Y1 - 2007

N2 - The problem of filtering information from large correlation matrices is of great importance in many applications. We have recently proposed the use of the Kullback-Leibler distance to measure the performance of filtering algorithms in recovering the underlying correlation matrix when the variables are described by a multivariate Gaussian distribution. Here we use the Kullback-Leibler distance to investigate the performance of filtering methods based on Random Matrix Theory and on the shrinkage technique. We also present some results on the application of the Kullback-Leibler distance to multivariate data which are non Gaussian distributed

AB - The problem of filtering information from large correlation matrices is of great importance in many applications. We have recently proposed the use of the Kullback-Leibler distance to measure the performance of filtering algorithms in recovering the underlying correlation matrix when the variables are described by a multivariate Gaussian distribution. Here we use the Kullback-Leibler distance to investigate the performance of filtering methods based on Random Matrix Theory and on the shrinkage technique. We also present some results on the application of the Kullback-Leibler distance to multivariate data which are non Gaussian distributed

UR - http://hdl.handle.net/10447/30988

M3 - Article

VL - 38

SP - 4079

EP - 4088

JO - Acta Physica Polonica B

JF - Acta Physica Polonica B

SN - 0587-4254

ER -