Nonparametric mixture of regression models

Mian Huang, Runze Li, Shaoli Wang

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Motivated by an analysis of U.S. house price index (HPI) data, we propose nonparametric finite mixture of regression models.We study the identifiability issue of the proposed models, and develop an estimation procedure by employing kernel regression.We further systematically study the sampling properties of the proposed estimators, and establish their asymptotic normality. A modified EM algorithm is proposed to carry out the estimation procedure. We show that our algorithm preserves the ascent property of the EM algorithm in an asymptotic sense. Monte Carlo simulations are conducted to examine the finite sample performance of the proposed estimation procedure. An empirical analysis of the U.S. HPI data is illustrated for the proposed methodology.

Original languageEnglish (US)
Pages (from-to)929-941
Number of pages13
JournalJournal of the American Statistical Association
Volume108
Issue number503
DOIs
StatePublished - Dec 16 2013

Fingerprint

Regression Model
EM Algorithm
Kernel Regression
Finite Mixture
Ascent
Identifiability
Empirical Analysis
Asymptotic Normality
Monte Carlo Simulation
Estimator
Methodology
Regression model
House price index
EM algorithm
Model
Sampling
Finite sample
Empirical analysis
Asymptotic normality
Finite mixture

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Huang, Mian ; Li, Runze ; Wang, Shaoli. / Nonparametric mixture of regression models. In: Journal of the American Statistical Association. 2013 ; Vol. 108, No. 503. pp. 929-941.
@article{d49c65b3d951476ebcfdc4d953f8139e,
title = "Nonparametric mixture of regression models",
abstract = "Motivated by an analysis of U.S. house price index (HPI) data, we propose nonparametric finite mixture of regression models.We study the identifiability issue of the proposed models, and develop an estimation procedure by employing kernel regression.We further systematically study the sampling properties of the proposed estimators, and establish their asymptotic normality. A modified EM algorithm is proposed to carry out the estimation procedure. We show that our algorithm preserves the ascent property of the EM algorithm in an asymptotic sense. Monte Carlo simulations are conducted to examine the finite sample performance of the proposed estimation procedure. An empirical analysis of the U.S. HPI data is illustrated for the proposed methodology.",
author = "Mian Huang and Runze Li and Shaoli Wang",
year = "2013",
month = "12",
day = "16",
doi = "10.1080/01621459.2013.772897",
language = "English (US)",
volume = "108",
pages = "929--941",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "503",

}

Nonparametric mixture of regression models. / Huang, Mian; Li, Runze; Wang, Shaoli.

In: Journal of the American Statistical Association, Vol. 108, No. 503, 16.12.2013, p. 929-941.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Nonparametric mixture of regression models

AU - Huang, Mian

AU - Li, Runze

AU - Wang, Shaoli

PY - 2013/12/16

Y1 - 2013/12/16

N2 - Motivated by an analysis of U.S. house price index (HPI) data, we propose nonparametric finite mixture of regression models.We study the identifiability issue of the proposed models, and develop an estimation procedure by employing kernel regression.We further systematically study the sampling properties of the proposed estimators, and establish their asymptotic normality. A modified EM algorithm is proposed to carry out the estimation procedure. We show that our algorithm preserves the ascent property of the EM algorithm in an asymptotic sense. Monte Carlo simulations are conducted to examine the finite sample performance of the proposed estimation procedure. An empirical analysis of the U.S. HPI data is illustrated for the proposed methodology.

AB - Motivated by an analysis of U.S. house price index (HPI) data, we propose nonparametric finite mixture of regression models.We study the identifiability issue of the proposed models, and develop an estimation procedure by employing kernel regression.We further systematically study the sampling properties of the proposed estimators, and establish their asymptotic normality. A modified EM algorithm is proposed to carry out the estimation procedure. We show that our algorithm preserves the ascent property of the EM algorithm in an asymptotic sense. Monte Carlo simulations are conducted to examine the finite sample performance of the proposed estimation procedure. An empirical analysis of the U.S. HPI data is illustrated for the proposed methodology.

UR - http://www.scopus.com/inward/record.url?scp=84890055402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890055402&partnerID=8YFLogxK

U2 - 10.1080/01621459.2013.772897

DO - 10.1080/01621459.2013.772897

M3 - Article

AN - SCOPUS:84890055402

VL - 108

SP - 929

EP - 941

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 503

ER -