A new class of improved estimators of a multinormal precision matrix

Dipak K. Dey; Malay Ghosh; C. Srinivasan

doi:10.1524/strm.1990.8.2.141

A new class of improved estimators of a multinormal precision matrix

Dipak K. Dey, Malay Ghosh, C. Srinivasan

Dr. Bing Zhang Department of Statistics

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

8 Scopus citations

Abstract

Stein and Haff's technique is used to obtain improved estimators of the multinormal precision matrix under a loss introduced by Efron and Morris (1976). The technique is to obtain solutions to a certain differential inequality involving the eigenvalues of the sample covariance matrix. A new class of improved estimators are obtained by solving the differential inequality.

Original language	English
Pages (from-to)	141-152
Number of pages	12
Journal	Statistics and Risk Modeling
Volume	8
Issue number	2
DOIs	https://doi.org/10.1524/strm.1990.8.2.141
State	Published - Feb 1990

Bibliographical note

Funding Information:
by AF0SR Grant Number 89-0225 supported by the NSF Grant Number by NSF EPSC0R Grant, RI1-8610671

Keywords

Wishart distribution
empirical Bayes estimators
matrix means
minimax estimators
precision matrix

ASJC Scopus subject areas

Statistics and Probability
Modeling and Simulation
Statistics, Probability and Uncertainty

Access to Document

10.1524/strm.1990.8.2.141

Cite this

@article{b206eaf5f2bd48159237c2991c64a87c,

title = "A new class of improved estimators of a multinormal precision matrix",

abstract = "Stein and Haff's technique is used to obtain improved estimators of the multinormal precision matrix under a loss introduced by Efron and Morris (1976). The technique is to obtain solutions to a certain differential inequality involving the eigenvalues of the sample covariance matrix. A new class of improved estimators are obtained by solving the differential inequality.",

keywords = "Wishart distribution, empirical Bayes estimators, matrix means, minimax estimators, precision matrix",

author = "Dey, {Dipak K.} and Malay Ghosh and C. Srinivasan",

note = "Funding Information: by AF0SR Grant Number 89-0225 supported by the NSF Grant Number by NSF EPSC0R Grant, RI1-8610671",

year = "1990",

month = feb,

doi = "10.1524/strm.1990.8.2.141",

language = "English",

volume = "8",

pages = "141--152",

number = "2",

}

TY - JOUR

T1 - A new class of improved estimators of a multinormal precision matrix

AU - Dey, Dipak K.

AU - Ghosh, Malay

AU - Srinivasan, C.

N1 - Funding Information: by AF0SR Grant Number 89-0225 supported by the NSF Grant Number by NSF EPSC0R Grant, RI1-8610671

PY - 1990/2

Y1 - 1990/2

N2 - Stein and Haff's technique is used to obtain improved estimators of the multinormal precision matrix under a loss introduced by Efron and Morris (1976). The technique is to obtain solutions to a certain differential inequality involving the eigenvalues of the sample covariance matrix. A new class of improved estimators are obtained by solving the differential inequality.

AB - Stein and Haff's technique is used to obtain improved estimators of the multinormal precision matrix under a loss introduced by Efron and Morris (1976). The technique is to obtain solutions to a certain differential inequality involving the eigenvalues of the sample covariance matrix. A new class of improved estimators are obtained by solving the differential inequality.

KW - Wishart distribution

KW - empirical Bayes estimators

KW - matrix means

KW - minimax estimators

KW - precision matrix

UR - http://www.scopus.com/inward/record.url?scp=84961480207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961480207&partnerID=8YFLogxK

U2 - 10.1524/strm.1990.8.2.141

DO - 10.1524/strm.1990.8.2.141

M3 - Article

AN - SCOPUS:84961480207

SN - 2193-1402

VL - 8

SP - 141

EP - 152

JO - Statistics and Risk Modeling

JF - Statistics and Risk Modeling

IS - 2

ER -

A new class of improved estimators of a multinormal precision matrix

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this