Semiparametric mixtures of regressions

David Russell Hunter, Derek S. Young

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

We present an algorithm for estimating parameters in a mixture-of-regressions model in which the errors are assumed to be independent and identically distributed but no other assumption is made. This model is introduced as one of several recent generalizations of the standard fully parametric mixture of linear regressions in the literature. A sufficient condition for the identifiability of the parameters is stated and proved. Several different versions of the algorithm, including one that has a provable ascent property, are introduced. Numerical tests indicate the effectiveness of some of these algorithms.

Original languageEnglish (US)
Pages (from-to)19-38
Number of pages20
JournalJournal of Nonparametric Statistics
Volume24
Issue number1
DOIs
StatePublished - Mar 1 2012

Fingerprint

Regression
Ascent
Identifiability
Linear regression
Identically distributed
Regression Model
Sufficient Conditions
Model
Standards
Generalization
Regression model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{28ecbe72de6c4a7fb0d0d44f3ecde4a6,
title = "Semiparametric mixtures of regressions",
abstract = "We present an algorithm for estimating parameters in a mixture-of-regressions model in which the errors are assumed to be independent and identically distributed but no other assumption is made. This model is introduced as one of several recent generalizations of the standard fully parametric mixture of linear regressions in the literature. A sufficient condition for the identifiability of the parameters is stated and proved. Several different versions of the algorithm, including one that has a provable ascent property, are introduced. Numerical tests indicate the effectiveness of some of these algorithms.",
author = "Hunter, {David Russell} and Young, {Derek S.}",
year = "2012",
month = "3",
day = "1",
doi = "10.1080/10485252.2011.608430",
language = "English (US)",
volume = "24",
pages = "19--38",
journal = "Journal of Nonparametric Statistics",
issn = "1048-5252",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

Semiparametric mixtures of regressions. / Hunter, David Russell; Young, Derek S.

In: Journal of Nonparametric Statistics, Vol. 24, No. 1, 01.03.2012, p. 19-38.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Semiparametric mixtures of regressions

AU - Hunter, David Russell

AU - Young, Derek S.

PY - 2012/3/1

Y1 - 2012/3/1

N2 - We present an algorithm for estimating parameters in a mixture-of-regressions model in which the errors are assumed to be independent and identically distributed but no other assumption is made. This model is introduced as one of several recent generalizations of the standard fully parametric mixture of linear regressions in the literature. A sufficient condition for the identifiability of the parameters is stated and proved. Several different versions of the algorithm, including one that has a provable ascent property, are introduced. Numerical tests indicate the effectiveness of some of these algorithms.

AB - We present an algorithm for estimating parameters in a mixture-of-regressions model in which the errors are assumed to be independent and identically distributed but no other assumption is made. This model is introduced as one of several recent generalizations of the standard fully parametric mixture of linear regressions in the literature. A sufficient condition for the identifiability of the parameters is stated and proved. Several different versions of the algorithm, including one that has a provable ascent property, are introduced. Numerical tests indicate the effectiveness of some of these algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84856920935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856920935&partnerID=8YFLogxK

U2 - 10.1080/10485252.2011.608430

DO - 10.1080/10485252.2011.608430

M3 - Article

AN - SCOPUS:84856920935

VL - 24

SP - 19

EP - 38

JO - Journal of Nonparametric Statistics

JF - Journal of Nonparametric Statistics

SN - 1048-5252

IS - 1

ER -