Moment-based Estimation of Mixtures of Regression Models

Claus Thorn Ekstrøm; Christian Bressen Pipper

Moment-based Estimation of Mixtures of Regression Models

Claus Thorn Ekstrøm, Christian Bressen Pipper

Biostatistisk afdeling

Abstract

Finite mixtures of regression models provide a flexible modeling framework for many phenomena. Using moment-based estimation of the regression parameters, we develop unbiased estimators with a minimum of assumptions on the mixture components. In particular, only the average regression model for one of the components in the mixture model is needed and no requirements on the distributions. The consistency and asymptotic distribution of the estimators is derived and the proposed method is validated through a series of simulation studies and is shown to be highly accurate. We illustrate the use of the moment-based mixture of regression models with an application to wine quality data.

Originalsprog	Udefineret/Ukendt
Tidsskrift	arXiv
Status	Udgivet - 15 maj 2019

Emneord

math.ST
stat.AP
stat.ME
stat.TH

Citationsformater

@article{d01439ba4a60425582176d85b41caddd,

title = "Moment-based Estimation of Mixtures of Regression Models",

abstract = " Finite mixtures of regression models provide a flexible modeling framework for many phenomena. Using moment-based estimation of the regression parameters, we develop unbiased estimators with a minimum of assumptions on the mixture components. In particular, only the average regression model for one of the components in the mixture model is needed and no requirements on the distributions. The consistency and asymptotic distribution of the estimators is derived and the proposed method is validated through a series of simulation studies and is shown to be highly accurate. We illustrate the use of the moment-based mixture of regression models with an application to wine quality data. ",

keywords = "math.ST, stat.AP, stat.ME, stat.TH",

author = "Ekstr{\o}m, {Claus Thorn} and Pipper, {Christian Bressen}",

note = "17 pages, 3 figures",

year = "2019",

month = may,

day = "15",

language = "Udefineret/Ukendt",

journal = "arXiv",

}

TY - JOUR

T1 - Moment-based Estimation of Mixtures of Regression Models

AU - Ekstrøm, Claus Thorn

AU - Pipper, Christian Bressen

N1 - 17 pages, 3 figures

PY - 2019/5/15

Y1 - 2019/5/15

N2 - Finite mixtures of regression models provide a flexible modeling framework for many phenomena. Using moment-based estimation of the regression parameters, we develop unbiased estimators with a minimum of assumptions on the mixture components. In particular, only the average regression model for one of the components in the mixture model is needed and no requirements on the distributions. The consistency and asymptotic distribution of the estimators is derived and the proposed method is validated through a series of simulation studies and is shown to be highly accurate. We illustrate the use of the moment-based mixture of regression models with an application to wine quality data.

AB - Finite mixtures of regression models provide a flexible modeling framework for many phenomena. Using moment-based estimation of the regression parameters, we develop unbiased estimators with a minimum of assumptions on the mixture components. In particular, only the average regression model for one of the components in the mixture model is needed and no requirements on the distributions. The consistency and asymptotic distribution of the estimators is derived and the proposed method is validated through a series of simulation studies and is shown to be highly accurate. We illustrate the use of the moment-based mixture of regression models with an application to wine quality data.

KW - math.ST

KW - stat.AP

KW - stat.ME

KW - stat.TH

M3 - Tidsskriftartikel

JO - arXiv

JF - arXiv

ER -