Estimation of partially linear regression models under the partial consistency property

Xia Cui, Ying Lu, Heng Peng

Research output: Contribution to journalArticle

Abstract

Utilizing recent theoretical results in high dimensional statistical modeling, a flexible yet computationally simple approach is proposed to estimate the partially linear models. Motivated by the partial consistency phenomena, the nonparametric component in the partially linear model is modeled via incidental parameters and estimated by a simple local average over small partitions of the support of the nonparametric variables. The proposed least-squares based method seeks to strike a balance between computation burden and efficiency of the estimators while minimizing model bias. It is shown that given inconsistent estimators of the nonparametric component, square root-n consistent estimators of the parameters of the parametric component can be obtained with little loss in efficiency. Moreover, conditional on the parametric estimates, an optimal estimator of the nonparametric component can be obtained using classic nonparametric methods. The statistical inference problems regarding the parametric parameters and a two-population nonparametric testing problem regarding the nonparametric component are considered. The results show that the behavior of the test statistics is satisfactory. To assess the performance of the new method in comparison with other methods, three simulation studies are conducted and a real data set about risk factors of birth weights is analyzed.

Original languageEnglish (US)
Pages (from-to)103-121
Number of pages19
JournalComputational Statistics and Data Analysis
Volume115
DOIs
StatePublished - Nov 1 2017

Fingerprint

Partially Linear Regression Model
Linear regression
Partial
Partially Linear Model
Estimator
Nonparametric Testing
Statistics
Consistent Estimator
Statistical Modeling
Nonparametric Methods
Risk Factors
Statistical Inference
Square root
Inconsistent
Estimate
Testing
Test Statistic
Least Squares
High-dimensional
Partition

Keywords

  • Asymptotic normality
  • Categorical data
  • High correlation
  • Nonparametric testing
  • Partial consistency
  • Partially linear model

ASJC Scopus subject areas

  • Statistics and Probability
  • Computational Theory and Mathematics
  • Computational Mathematics
  • Applied Mathematics

Cite this

Estimation of partially linear regression models under the partial consistency property. / Cui, Xia; Lu, Ying; Peng, Heng.

In: Computational Statistics and Data Analysis, Vol. 115, 01.11.2017, p. 103-121.

Research output: Contribution to journalArticle

@article{73e26af4b4fb485f81bb8051bd15ac39,
title = "Estimation of partially linear regression models under the partial consistency property",
abstract = "Utilizing recent theoretical results in high dimensional statistical modeling, a flexible yet computationally simple approach is proposed to estimate the partially linear models. Motivated by the partial consistency phenomena, the nonparametric component in the partially linear model is modeled via incidental parameters and estimated by a simple local average over small partitions of the support of the nonparametric variables. The proposed least-squares based method seeks to strike a balance between computation burden and efficiency of the estimators while minimizing model bias. It is shown that given inconsistent estimators of the nonparametric component, square root-n consistent estimators of the parameters of the parametric component can be obtained with little loss in efficiency. Moreover, conditional on the parametric estimates, an optimal estimator of the nonparametric component can be obtained using classic nonparametric methods. The statistical inference problems regarding the parametric parameters and a two-population nonparametric testing problem regarding the nonparametric component are considered. The results show that the behavior of the test statistics is satisfactory. To assess the performance of the new method in comparison with other methods, three simulation studies are conducted and a real data set about risk factors of birth weights is analyzed.",
keywords = "Asymptotic normality, Categorical data, High correlation, Nonparametric testing, Partial consistency, Partially linear model",
author = "Xia Cui and Ying Lu and Heng Peng",
year = "2017",
month = "11",
day = "1",
doi = "10.1016/j.csda.2017.05.004",
language = "English (US)",
volume = "115",
pages = "103--121",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

TY - JOUR

T1 - Estimation of partially linear regression models under the partial consistency property

AU - Cui, Xia

AU - Lu, Ying

AU - Peng, Heng

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Utilizing recent theoretical results in high dimensional statistical modeling, a flexible yet computationally simple approach is proposed to estimate the partially linear models. Motivated by the partial consistency phenomena, the nonparametric component in the partially linear model is modeled via incidental parameters and estimated by a simple local average over small partitions of the support of the nonparametric variables. The proposed least-squares based method seeks to strike a balance between computation burden and efficiency of the estimators while minimizing model bias. It is shown that given inconsistent estimators of the nonparametric component, square root-n consistent estimators of the parameters of the parametric component can be obtained with little loss in efficiency. Moreover, conditional on the parametric estimates, an optimal estimator of the nonparametric component can be obtained using classic nonparametric methods. The statistical inference problems regarding the parametric parameters and a two-population nonparametric testing problem regarding the nonparametric component are considered. The results show that the behavior of the test statistics is satisfactory. To assess the performance of the new method in comparison with other methods, three simulation studies are conducted and a real data set about risk factors of birth weights is analyzed.

AB - Utilizing recent theoretical results in high dimensional statistical modeling, a flexible yet computationally simple approach is proposed to estimate the partially linear models. Motivated by the partial consistency phenomena, the nonparametric component in the partially linear model is modeled via incidental parameters and estimated by a simple local average over small partitions of the support of the nonparametric variables. The proposed least-squares based method seeks to strike a balance between computation burden and efficiency of the estimators while minimizing model bias. It is shown that given inconsistent estimators of the nonparametric component, square root-n consistent estimators of the parameters of the parametric component can be obtained with little loss in efficiency. Moreover, conditional on the parametric estimates, an optimal estimator of the nonparametric component can be obtained using classic nonparametric methods. The statistical inference problems regarding the parametric parameters and a two-population nonparametric testing problem regarding the nonparametric component are considered. The results show that the behavior of the test statistics is satisfactory. To assess the performance of the new method in comparison with other methods, three simulation studies are conducted and a real data set about risk factors of birth weights is analyzed.

KW - Asymptotic normality

KW - Categorical data

KW - High correlation

KW - Nonparametric testing

KW - Partial consistency

KW - Partially linear model

UR - http://www.scopus.com/inward/record.url?scp=85021297047&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021297047&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2017.05.004

DO - 10.1016/j.csda.2017.05.004

M3 - Article

VL - 115

SP - 103

EP - 121

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

ER -