EM estimation for finite mixture models with known mixture component size

Chen Teel, Taeyoung Park, Allan R. Sampson

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We consider the use of an EM algorithm for fitting finite mixture models when mixture component size is known. This situation can occur in a number of settings, where individual membership is unknown but aggregate membership is known. When the mixture component size, i.e., the aggregate mixture component membership, is known, it is common practice to treat only the mixing probability as known. This approach does not, however, entirely account for the fact that the number of observations within each mixture component is known, which may result in artificially incorrect estimates of parameters. By fully capitalizing on the available information, the proposed EM algorithm shows robustness to the choice of starting values and exhibits numerically stable convergence properties.

Original languageEnglish
Pages (from-to)1545-1556
Number of pages12
JournalCommunications in Statistics: Simulation and Computation
Volume44
Issue number6
DOIs
Publication statusPublished - 2015 Jul 3

Fingerprint

Finite Mixture Models
EM Algorithm
Stable Convergence
Convergence Properties
Robustness
Unknown
Estimate

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation

Cite this

@article{a7665f827c38473cae8d0eb3b27509a7,
title = "EM estimation for finite mixture models with known mixture component size",
abstract = "We consider the use of an EM algorithm for fitting finite mixture models when mixture component size is known. This situation can occur in a number of settings, where individual membership is unknown but aggregate membership is known. When the mixture component size, i.e., the aggregate mixture component membership, is known, it is common practice to treat only the mixing probability as known. This approach does not, however, entirely account for the fact that the number of observations within each mixture component is known, which may result in artificially incorrect estimates of parameters. By fully capitalizing on the available information, the proposed EM algorithm shows robustness to the choice of starting values and exhibits numerically stable convergence properties.",
author = "Chen Teel and Taeyoung Park and Sampson, {Allan R.}",
year = "2015",
month = "7",
day = "3",
doi = "10.1080/03610918.2013.824091",
language = "English",
volume = "44",
pages = "1545--1556",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

EM estimation for finite mixture models with known mixture component size. / Teel, Chen; Park, Taeyoung; Sampson, Allan R.

In: Communications in Statistics: Simulation and Computation, Vol. 44, No. 6, 03.07.2015, p. 1545-1556.

Research output: Contribution to journalArticle

TY - JOUR

T1 - EM estimation for finite mixture models with known mixture component size

AU - Teel, Chen

AU - Park, Taeyoung

AU - Sampson, Allan R.

PY - 2015/7/3

Y1 - 2015/7/3

N2 - We consider the use of an EM algorithm for fitting finite mixture models when mixture component size is known. This situation can occur in a number of settings, where individual membership is unknown but aggregate membership is known. When the mixture component size, i.e., the aggregate mixture component membership, is known, it is common practice to treat only the mixing probability as known. This approach does not, however, entirely account for the fact that the number of observations within each mixture component is known, which may result in artificially incorrect estimates of parameters. By fully capitalizing on the available information, the proposed EM algorithm shows robustness to the choice of starting values and exhibits numerically stable convergence properties.

AB - We consider the use of an EM algorithm for fitting finite mixture models when mixture component size is known. This situation can occur in a number of settings, where individual membership is unknown but aggregate membership is known. When the mixture component size, i.e., the aggregate mixture component membership, is known, it is common practice to treat only the mixing probability as known. This approach does not, however, entirely account for the fact that the number of observations within each mixture component is known, which may result in artificially incorrect estimates of parameters. By fully capitalizing on the available information, the proposed EM algorithm shows robustness to the choice of starting values and exhibits numerically stable convergence properties.

UR - http://www.scopus.com/inward/record.url?scp=84918561994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84918561994&partnerID=8YFLogxK

U2 - 10.1080/03610918.2013.824091

DO - 10.1080/03610918.2013.824091

M3 - Article

VL - 44

SP - 1545

EP - 1556

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 6

ER -