EM algorithms for multivariate Gaussian mixture models with truncated and censored data

Gyemin Lee; Clayton Scott

doi:10.1016/j.csda.2012.03.003

EM algorithms for multivariate Gaussian mixture models with truncated and censored data

Gyemin Lee, Clayton Scott

Dept. of Information Technology and Media Engineering

University of Michigan, Ann Arbor

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

107 Scopus citations

Abstract

We present expectation-maximization (EM) algorithms for fitting multivariate Gaussian mixture models to data that are truncated, censored or truncated and censored. These two types of incomplete measurements are naturally handled together through their relation to the multivariate truncated Gaussian distribution. We illustrate our algorithms on synthetic and flow cytometry data.

Original language	English
Pages (from-to)	2816-2829
Number of pages	14
Journal	Computational Statistics and Data Analysis
Volume	56
Issue number	9
DOIs	https://doi.org/10.1016/j.csda.2012.03.003
State	Published - Sep 2012

Keywords

Censoring
EM algorithm
Multivariate Gaussian mixture model
Multivariate truncated Gaussian distribution
Truncation

Access to Document

10.1016/j.csda.2012.03.003

Cite this

@article{9ea9026c8d5e47068d6cb266711ad342,

title = "EM algorithms for multivariate Gaussian mixture models with truncated and censored data",

abstract = "We present expectation-maximization (EM) algorithms for fitting multivariate Gaussian mixture models to data that are truncated, censored or truncated and censored. These two types of incomplete measurements are naturally handled together through their relation to the multivariate truncated Gaussian distribution. We illustrate our algorithms on synthetic and flow cytometry data.",

keywords = "Censoring, EM algorithm, Multivariate Gaussian mixture model, Multivariate truncated Gaussian distribution, Truncation",

author = "Gyemin Lee and Clayton Scott",

year = "2012",

month = sep,

doi = "10.1016/j.csda.2012.03.003",

language = "English",

volume = "56",

pages = "2816--2829",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

number = "9",

}

TY - JOUR

T1 - EM algorithms for multivariate Gaussian mixture models with truncated and censored data

AU - Lee, Gyemin

AU - Scott, Clayton

PY - 2012/9

Y1 - 2012/9

N2 - We present expectation-maximization (EM) algorithms for fitting multivariate Gaussian mixture models to data that are truncated, censored or truncated and censored. These two types of incomplete measurements are naturally handled together through their relation to the multivariate truncated Gaussian distribution. We illustrate our algorithms on synthetic and flow cytometry data.

AB - We present expectation-maximization (EM) algorithms for fitting multivariate Gaussian mixture models to data that are truncated, censored or truncated and censored. These two types of incomplete measurements are naturally handled together through their relation to the multivariate truncated Gaussian distribution. We illustrate our algorithms on synthetic and flow cytometry data.

KW - Censoring

KW - EM algorithm

KW - Multivariate Gaussian mixture model

KW - Multivariate truncated Gaussian distribution

KW - Truncation

UR - http://www.scopus.com/inward/record.url?scp=84859898681&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2012.03.003

DO - 10.1016/j.csda.2012.03.003

M3 - Article

AN - SCOPUS:84859898681

SN - 0167-9473

VL - 56

SP - 2816

EP - 2829

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

IS - 9

ER -

EM algorithms for multivariate Gaussian mixture models with truncated and censored data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this