Methods of L1 estimation of a covariance matrix

Jacqueline S. Galpin; Douglas M. Hawkins

doi:10.1016/0167-9473(87)90054-5

Methods of L₁ estimation of a covariance matrix

Jacqueline S. Galpin, Douglas M. Hawkins

Statistics (Twin Cities)

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

30 Scopus citations

Abstract

The classical relationship between the spectral decomposition of a covariance matrix and the estimation of its principal components is utilized in obtaining robust covariance matrix estimates from robust estimates of the principal components, based on L₁ formulations. The performance of these estimates is studied using some problematical data sets discussed in the literature.

Original language	English (US)
Pages (from-to)	305-319
Number of pages	15
Journal	Computational Statistics and Data Analysis
Volume	5
Issue number	4
DOIs	https://doi.org/10.1016/0167-9473(87)90054-5
State	Published - Sep 1987

Keywords

Covariance matrix estimation
L norm
Linear and quadratic programming
Principal component estimation
Robust estimation

Publisher link

10.1016/0167-9473(87)90054-5

Find It

Find It at U of M Libraries

Cite this

@article{eff0a8e861724d2bab68f88fcb6ade89,

title = "Methods of L1 estimation of a covariance matrix",

abstract = "The classical relationship between the spectral decomposition of a covariance matrix and the estimation of its principal components is utilized in obtaining robust covariance matrix estimates from robust estimates of the principal components, based on L1 formulations. The performance of these estimates is studied using some problematical data sets discussed in the literature.",

keywords = "Covariance matrix estimation, L norm, Linear and quadratic programming, Principal component estimation, Robust estimation",

author = "Galpin, {Jacqueline S.} and Hawkins, {Douglas M.}",

year = "1987",

month = sep,

doi = "10.1016/0167-9473(87)90054-5",

language = "English (US)",

volume = "5",

pages = "305--319",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

publisher = "Elsevier B.V.",

number = "4",

}

TY - JOUR

T1 - Methods of L1 estimation of a covariance matrix

AU - Galpin, Jacqueline S.

AU - Hawkins, Douglas M.

PY - 1987/9

Y1 - 1987/9

N2 - The classical relationship between the spectral decomposition of a covariance matrix and the estimation of its principal components is utilized in obtaining robust covariance matrix estimates from robust estimates of the principal components, based on L1 formulations. The performance of these estimates is studied using some problematical data sets discussed in the literature.

AB - The classical relationship between the spectral decomposition of a covariance matrix and the estimation of its principal components is utilized in obtaining robust covariance matrix estimates from robust estimates of the principal components, based on L1 formulations. The performance of these estimates is studied using some problematical data sets discussed in the literature.

KW - Covariance matrix estimation

KW - L norm

KW - Linear and quadratic programming

KW - Principal component estimation

KW - Robust estimation

UR - http://www.scopus.com/inward/record.url?scp=38249035112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38249035112&partnerID=8YFLogxK

U2 - 10.1016/0167-9473(87)90054-5

DO - 10.1016/0167-9473(87)90054-5

M3 - Article

AN - SCOPUS:38249035112

SN - 0167-9473

VL - 5

SP - 305

EP - 319

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

IS - 4

ER -