Relation between the covariance and Fisher information matrices

Abram Kagan; Zinoviy Landsman

doi:10.1016/s0167-7152(98)00178-3

Relation between the covariance and Fisher information matrices

Abram Kagan, Zinoviy Landsman

Department of Statistics

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

Abstract

It is proved that for any two positive definite Hermitian m×m matrices I and V subject to I≥V^-1there exists an m-variate random vector X with V as its covariance matrix and I its matrix of Fisher information.

Original language	English
Pages (from-to)	7-13
Number of pages	7
Journal	Statistics and Probability Letters
Volume	42
Issue number	1
DOIs	https://doi.org/10.1016/s0167-7152(98)00178-3
State	Published - 15 Mar 1999

Keywords

Covariance
Fisher information matrix
Primary 62810

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1016/s0167-7152(98)00178-3

Cite this

@article{c99b7efdf5bc418f8a8f87fe027ed1b1,

title = "Relation between the covariance and Fisher information matrices",

abstract = "It is proved that for any two positive definite Hermitian m×m matrices I and V subject to I≥V-1there exists an m-variate random vector X with V as its covariance matrix and I its matrix of Fisher information.",

keywords = "Covariance, Fisher information matrix, Primary 62810",

author = "Abram Kagan and Zinoviy Landsman",

year = "1999",

month = mar,

day = "15",

doi = "10.1016/s0167-7152(98)00178-3",

language = "English",

volume = "42",

pages = "7--13",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Relation between the covariance and Fisher information matrices

AU - Kagan, Abram

AU - Landsman, Zinoviy

PY - 1999/3/15

Y1 - 1999/3/15

N2 - It is proved that for any two positive definite Hermitian m×m matrices I and V subject to I≥V-1there exists an m-variate random vector X with V as its covariance matrix and I its matrix of Fisher information.

AB - It is proved that for any two positive definite Hermitian m×m matrices I and V subject to I≥V-1there exists an m-variate random vector X with V as its covariance matrix and I its matrix of Fisher information.

KW - Covariance

KW - Fisher information matrix

KW - Primary 62810

UR - http://www.scopus.com/inward/record.url?scp=0038128273&partnerID=8YFLogxK

U2 - 10.1016/s0167-7152(98)00178-3

DO - 10.1016/s0167-7152(98)00178-3

M3 - Article

AN - SCOPUS:0038128273

SN - 0167-7152

VL - 42

SP - 7

EP - 13

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

IS - 1

ER -

Relation between the covariance and Fisher information matrices

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this