Mixture Models in Statistics

Ehud Makov

doi:10.1016/B0-08-043076-7/00464-2

Mixture Models in Statistics

Ehud Makov

Department of Statistics

Research output: Chapter in Book/Report/Conference proceeding › Entry for encyclopedia/dictionary › peer-review

Abstract

Mixture models are a discrete or continuous weighted combination of distributions aimed at representing a heterogeneous population comprising of several (two or more) distinct subpopulations. Such models are often used to approximate nonstandard distributions when the underlying population can be regarded as homogenous. A mathematical definition of mixture models is provided, several of the diverse applications of such models are outlined, and the main methods of estimating the model's parameters are discussed.

Original language	English
Title of host publication	International Encyclopedia of the Social & Behavioral Sciences
Publisher	Elsevier Science Ltd.
Pages	9910-9915
ISBN (Print)	9780080430768
DOIs	https://doi.org/10.1016/B0-08-043076-7/00464-2
State	Published - 2001

Access to Document

10.1016/B0-08-043076-7/00464-2

Cite this

@inbook{f0114efa5588425c9bf38b497bdd7a9c,

title = "Mixture Models in Statistics",

abstract = "Mixture models are a discrete or continuous weighted combination of distributions aimed at representing a heterogeneous population comprising of several (two or more) distinct subpopulations. Such models are often used to approximate nonstandard distributions when the underlying population can be regarded as homogenous. A mathematical definition of mixture models is provided, several of the diverse applications of such models are outlined, and the main methods of estimating the model's parameters are discussed.",

author = "Ehud Makov",

year = "2001",

doi = "10.1016/B0-08-043076-7/00464-2",

language = "English",

isbn = "9780080430768",

pages = "9910--9915",

booktitle = "International Encyclopedia of the Social & Behavioral Sciences",

publisher = "Elsevier Science Ltd.",

}

TY - CHAP

T1 - Mixture Models in Statistics

AU - Makov, Ehud

PY - 2001

Y1 - 2001

N2 - Mixture models are a discrete or continuous weighted combination of distributions aimed at representing a heterogeneous population comprising of several (two or more) distinct subpopulations. Such models are often used to approximate nonstandard distributions when the underlying population can be regarded as homogenous. A mathematical definition of mixture models is provided, several of the diverse applications of such models are outlined, and the main methods of estimating the model's parameters are discussed.

AB - Mixture models are a discrete or continuous weighted combination of distributions aimed at representing a heterogeneous population comprising of several (two or more) distinct subpopulations. Such models are often used to approximate nonstandard distributions when the underlying population can be regarded as homogenous. A mathematical definition of mixture models is provided, several of the diverse applications of such models are outlined, and the main methods of estimating the model's parameters are discussed.

U2 - 10.1016/B0-08-043076-7/00464-2

DO - 10.1016/B0-08-043076-7/00464-2

M3 - Entry for encyclopedia/dictionary

SN - 9780080430768

SP - 9910

EP - 9915

BT - International Encyclopedia of the Social & Behavioral Sciences

PB - Elsevier Science Ltd.

ER -

Mixture Models in Statistics

Abstract

Access to Document

Fingerprint

Cite this