Flexible estimation of a semiparametric two-component mixture model with one parametric component

Yanyuan Ma, Weixin Yao

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We study a two-component semiparametric mixture model where one component distribution belongs to a parametric class, while the other is symmetric but otherwise arbitrary. This semiparametric model has wide applications in many areas such as large-scale simultaneous testing/multiple testing, sequential clustering, and robust modeling. We develop a class of estimators that are surprisingly simple and are unique in terms of their construction. A unique feature of these methods is that they do not rely on the estimation of the nonparametric component of the model. Instead, the methods only require a working model of the unspecified distribution, which may or may not reflect the true distribution. In addition, we establish connections between the existing estimator and the new methods and further derive a semiparametric efficient estimator. We compare our estimators with the existing method and investigate the advantages and cost of the relatively simple estimation procedure.

Original languageEnglish (US)
Pages (from-to)444-474
Number of pages31
JournalElectronic Journal of Statistics
Volume9
DOIs
StatePublished - Jan 1 2015

Fingerprint

Component Model
Mixture Model
Semiparametric Model
Estimator
Efficient Estimator
Multiple Testing
Clustering
Testing
Mixture model
Costs
Arbitrary
Modeling
Model
Class

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{5e2d8ecc8ae246ddbdd9a03fc5ca7b79,
title = "Flexible estimation of a semiparametric two-component mixture model with one parametric component",
abstract = "We study a two-component semiparametric mixture model where one component distribution belongs to a parametric class, while the other is symmetric but otherwise arbitrary. This semiparametric model has wide applications in many areas such as large-scale simultaneous testing/multiple testing, sequential clustering, and robust modeling. We develop a class of estimators that are surprisingly simple and are unique in terms of their construction. A unique feature of these methods is that they do not rely on the estimation of the nonparametric component of the model. Instead, the methods only require a working model of the unspecified distribution, which may or may not reflect the true distribution. In addition, we establish connections between the existing estimator and the new methods and further derive a semiparametric efficient estimator. We compare our estimators with the existing method and investigate the advantages and cost of the relatively simple estimation procedure.",
author = "Yanyuan Ma and Weixin Yao",
year = "2015",
month = "1",
day = "1",
doi = "10.1214/15-EJS1008",
language = "English (US)",
volume = "9",
pages = "444--474",
journal = "Electronic Journal of Statistics",
issn = "1935-7524",
publisher = "Institute of Mathematical Statistics",

}

Flexible estimation of a semiparametric two-component mixture model with one parametric component. / Ma, Yanyuan; Yao, Weixin.

In: Electronic Journal of Statistics, Vol. 9, 01.01.2015, p. 444-474.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Flexible estimation of a semiparametric two-component mixture model with one parametric component

AU - Ma, Yanyuan

AU - Yao, Weixin

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We study a two-component semiparametric mixture model where one component distribution belongs to a parametric class, while the other is symmetric but otherwise arbitrary. This semiparametric model has wide applications in many areas such as large-scale simultaneous testing/multiple testing, sequential clustering, and robust modeling. We develop a class of estimators that are surprisingly simple and are unique in terms of their construction. A unique feature of these methods is that they do not rely on the estimation of the nonparametric component of the model. Instead, the methods only require a working model of the unspecified distribution, which may or may not reflect the true distribution. In addition, we establish connections between the existing estimator and the new methods and further derive a semiparametric efficient estimator. We compare our estimators with the existing method and investigate the advantages and cost of the relatively simple estimation procedure.

AB - We study a two-component semiparametric mixture model where one component distribution belongs to a parametric class, while the other is symmetric but otherwise arbitrary. This semiparametric model has wide applications in many areas such as large-scale simultaneous testing/multiple testing, sequential clustering, and robust modeling. We develop a class of estimators that are surprisingly simple and are unique in terms of their construction. A unique feature of these methods is that they do not rely on the estimation of the nonparametric component of the model. Instead, the methods only require a working model of the unspecified distribution, which may or may not reflect the true distribution. In addition, we establish connections between the existing estimator and the new methods and further derive a semiparametric efficient estimator. We compare our estimators with the existing method and investigate the advantages and cost of the relatively simple estimation procedure.

UR - http://www.scopus.com/inward/record.url?scp=84926349045&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926349045&partnerID=8YFLogxK

U2 - 10.1214/15-EJS1008

DO - 10.1214/15-EJS1008

M3 - Article

AN - SCOPUS:84926349045

VL - 9

SP - 444

EP - 474

JO - Electronic Journal of Statistics

JF - Electronic Journal of Statistics

SN - 1935-7524

ER -