A family of discrete multivariate maximum-entropy distributions

David Hessen

doi:10.1111/stan.70011

A family of discrete multivariate maximum-entropy distributions

David Hessen

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

Abstract

A family of multivariate maximum-entropy distributions with general discrete support is derived. Members of the family are distinguished from each other by different specified sets of joint non-central moments. One of the members can be viewed as a discrete analogue of the continuous multivariate normal distribution. In an illustrative example, maximum likelihood estimation is used in fitting several bivariate discrete maximum-entropy distributions to empirical data.

Original language	English
Article number	e70011
Number of pages	8
Journal	Statistica Neerlandica
Volume	79
Issue number	3
DOIs	https://doi.org/10.1111/stan.70011
Publication status	Published - 24 May 2025

Bibliographical note

Publisher Copyright:
© 2025 The Author(s). Statistica Neerlandica published by John Wiley & Sons Ltd on behalf of Netherlands Society for Statistics and Operations Research.

Keywords

discrete support
exponential family
maximum-entropy
multivariate normal distribution

Access to Document

10.1111/stan.70011Licence: CC BY

Statistica Neerlandica - 2025 - Hessen - A family of discrete multivariate maximum‐entropy distributionsFinal published version, 359 KBLicence: CC BY

Cite this

@article{450c6f6632d744bf88f2972bdc171cef,

title = "A family of discrete multivariate maximum-entropy distributions",

abstract = "A family of multivariate maximum-entropy distributions with general discrete support is derived. Members of the family are distinguished from each other by different specified sets of joint non-central moments. One of the members can be viewed as a discrete analogue of the continuous multivariate normal distribution. In an illustrative example, maximum likelihood estimation is used in fitting several bivariate discrete maximum-entropy distributions to empirical data.",

keywords = "discrete support, exponential family, maximum-entropy, multivariate normal distribution",

author = "David Hessen",

note = "Publisher Copyright: {\textcopyright} 2025 The Author(s). Statistica Neerlandica published by John Wiley \& Sons Ltd on behalf of Netherlands Society for Statistics and Operations Research.",

year = "2025",

month = may,

day = "24",

doi = "10.1111/stan.70011",

language = "English",

volume = "79",

journal = "Statistica Neerlandica",

issn = "0039-0402",

publisher = "Wiley-Blackwell Publishing Ltd",

number = "3",

}

TY - JOUR

T1 - A family of discrete multivariate maximum-entropy distributions

AU - Hessen, David

PY - 2025/5/24

Y1 - 2025/5/24

N2 - A family of multivariate maximum-entropy distributions with general discrete support is derived. Members of the family are distinguished from each other by different specified sets of joint non-central moments. One of the members can be viewed as a discrete analogue of the continuous multivariate normal distribution. In an illustrative example, maximum likelihood estimation is used in fitting several bivariate discrete maximum-entropy distributions to empirical data.

AB - A family of multivariate maximum-entropy distributions with general discrete support is derived. Members of the family are distinguished from each other by different specified sets of joint non-central moments. One of the members can be viewed as a discrete analogue of the continuous multivariate normal distribution. In an illustrative example, maximum likelihood estimation is used in fitting several bivariate discrete maximum-entropy distributions to empirical data.

KW - discrete support

KW - exponential family

KW - maximum-entropy

KW - multivariate normal distribution

U2 - 10.1111/stan.70011

DO - 10.1111/stan.70011

M3 - Article

SN - 0039-0402

VL - 79

JO - Statistica Neerlandica

JF - Statistica Neerlandica

IS - 3

M1 - e70011

ER -

A family of discrete multivariate maximum-entropy distributions

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this