Estimation and inference of error-prone covariate effect in the presence of confounding variables

Jianxuan Liu, Yanyuan Ma, Liping Zhu, Raymond J. Carroll

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We introduce a general single index semiparametric measurement error model for the case that the main covariate of interest is measured with error and modeled parametrically, and where there are many other variables also important to the modeling. We propose a semiparametric bias-correction approach to estimate the effect of the covariate of interest. The resultant estimators are shown to be root-n consistent, asymptotically normal and locally efficient. Comprehensive simulations and an analysis of an empirical data set are performed to demonstrate the finite sample performance and the bias reduction of the locally efficient estimators.

Original languageEnglish (US)
Pages (from-to)480-501
Number of pages22
JournalElectronic Journal of Statistics
Volume11
Issue number1
DOIs
StatePublished - Jan 1 2017

Fingerprint

Confounding
Covariates
Bias Reduction
Measurement Error Model
Bias Correction
Efficient Estimator
Roots
Estimator
Modeling
Estimate
Demonstrate
Simulation
Inference
Empirical data
Finite sample
Measurement error
Bias correction
Bias reduction

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{baf3ee0e98904debbe5706266f762f60,
title = "Estimation and inference of error-prone covariate effect in the presence of confounding variables",
abstract = "We introduce a general single index semiparametric measurement error model for the case that the main covariate of interest is measured with error and modeled parametrically, and where there are many other variables also important to the modeling. We propose a semiparametric bias-correction approach to estimate the effect of the covariate of interest. The resultant estimators are shown to be root-n consistent, asymptotically normal and locally efficient. Comprehensive simulations and an analysis of an empirical data set are performed to demonstrate the finite sample performance and the bias reduction of the locally efficient estimators.",
author = "Jianxuan Liu and Yanyuan Ma and Liping Zhu and Carroll, {Raymond J.}",
year = "2017",
month = "1",
day = "1",
doi = "10.1214/17-EJS1242",
language = "English (US)",
volume = "11",
pages = "480--501",
journal = "Electronic Journal of Statistics",
issn = "1935-7524",
publisher = "Institute of Mathematical Statistics",
number = "1",

}

Estimation and inference of error-prone covariate effect in the presence of confounding variables. / Liu, Jianxuan; Ma, Yanyuan; Zhu, Liping; Carroll, Raymond J.

In: Electronic Journal of Statistics, Vol. 11, No. 1, 01.01.2017, p. 480-501.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Estimation and inference of error-prone covariate effect in the presence of confounding variables

AU - Liu, Jianxuan

AU - Ma, Yanyuan

AU - Zhu, Liping

AU - Carroll, Raymond J.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We introduce a general single index semiparametric measurement error model for the case that the main covariate of interest is measured with error and modeled parametrically, and where there are many other variables also important to the modeling. We propose a semiparametric bias-correction approach to estimate the effect of the covariate of interest. The resultant estimators are shown to be root-n consistent, asymptotically normal and locally efficient. Comprehensive simulations and an analysis of an empirical data set are performed to demonstrate the finite sample performance and the bias reduction of the locally efficient estimators.

AB - We introduce a general single index semiparametric measurement error model for the case that the main covariate of interest is measured with error and modeled parametrically, and where there are many other variables also important to the modeling. We propose a semiparametric bias-correction approach to estimate the effect of the covariate of interest. The resultant estimators are shown to be root-n consistent, asymptotically normal and locally efficient. Comprehensive simulations and an analysis of an empirical data set are performed to demonstrate the finite sample performance and the bias reduction of the locally efficient estimators.

UR - http://www.scopus.com/inward/record.url?scp=85014747683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014747683&partnerID=8YFLogxK

U2 - 10.1214/17-EJS1242

DO - 10.1214/17-EJS1242

M3 - Article

C2 - 28983388

AN - SCOPUS:85014747683

VL - 11

SP - 480

EP - 501

JO - Electronic Journal of Statistics

JF - Electronic Journal of Statistics

SN - 1935-7524

IS - 1

ER -