Simultaneous treatment of unspecified heteroskedastic model error distribution and mismeasured covariates for restricted moment models

Tanya P. Garcia, Yanyuan Ma

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We develop consistent and efficient estimation of parameters in general regression models with mismeasured covariates. We assume the model error and covariate distributions are unspecified, and the measurement error distribution is a general parametric distribution with unknown variance–covariance. We construct root-n consistent, asymptotically normal and locally efficient estimators using the semiparametric efficient score. We do not estimate any unknown distribution or model error heteroskedasticity. Instead, we form the estimator under possibly incorrect working distribution models for the model error, error-prone covariate, or both. Empirical results demonstrate robustness to different incorrect working models in homoscedastic and heteroskedastic models with error-prone covariates.

Original languageEnglish (US)
Pages (from-to)194-206
Number of pages13
JournalJournal of Econometrics
Volume200
Issue number2
DOIs
StatePublished - Oct 1 2017

Fingerprint

Covariates
Estimator
Regression model
Efficient estimation
Empirical results
Robustness
Measurement error
Heteroskedasticity

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

@article{197041f70da84932b744de4cdcc9bf0a,
title = "Simultaneous treatment of unspecified heteroskedastic model error distribution and mismeasured covariates for restricted moment models",
abstract = "We develop consistent and efficient estimation of parameters in general regression models with mismeasured covariates. We assume the model error and covariate distributions are unspecified, and the measurement error distribution is a general parametric distribution with unknown variance–covariance. We construct root-n consistent, asymptotically normal and locally efficient estimators using the semiparametric efficient score. We do not estimate any unknown distribution or model error heteroskedasticity. Instead, we form the estimator under possibly incorrect working distribution models for the model error, error-prone covariate, or both. Empirical results demonstrate robustness to different incorrect working models in homoscedastic and heteroskedastic models with error-prone covariates.",
author = "Garcia, {Tanya P.} and Yanyuan Ma",
year = "2017",
month = "10",
day = "1",
doi = "10.1016/j.jeconom.2017.06.005",
language = "English (US)",
volume = "200",
pages = "194--206",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

Simultaneous treatment of unspecified heteroskedastic model error distribution and mismeasured covariates for restricted moment models. / Garcia, Tanya P.; Ma, Yanyuan.

In: Journal of Econometrics, Vol. 200, No. 2, 01.10.2017, p. 194-206.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Simultaneous treatment of unspecified heteroskedastic model error distribution and mismeasured covariates for restricted moment models

AU - Garcia, Tanya P.

AU - Ma, Yanyuan

PY - 2017/10/1

Y1 - 2017/10/1

N2 - We develop consistent and efficient estimation of parameters in general regression models with mismeasured covariates. We assume the model error and covariate distributions are unspecified, and the measurement error distribution is a general parametric distribution with unknown variance–covariance. We construct root-n consistent, asymptotically normal and locally efficient estimators using the semiparametric efficient score. We do not estimate any unknown distribution or model error heteroskedasticity. Instead, we form the estimator under possibly incorrect working distribution models for the model error, error-prone covariate, or both. Empirical results demonstrate robustness to different incorrect working models in homoscedastic and heteroskedastic models with error-prone covariates.

AB - We develop consistent and efficient estimation of parameters in general regression models with mismeasured covariates. We assume the model error and covariate distributions are unspecified, and the measurement error distribution is a general parametric distribution with unknown variance–covariance. We construct root-n consistent, asymptotically normal and locally efficient estimators using the semiparametric efficient score. We do not estimate any unknown distribution or model error heteroskedasticity. Instead, we form the estimator under possibly incorrect working distribution models for the model error, error-prone covariate, or both. Empirical results demonstrate robustness to different incorrect working models in homoscedastic and heteroskedastic models with error-prone covariates.

UR - http://www.scopus.com/inward/record.url?scp=85026542615&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026542615&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2017.06.005

DO - 10.1016/j.jeconom.2017.06.005

M3 - Article

C2 - 29200600

AN - SCOPUS:85026542615

VL - 200

SP - 194

EP - 206

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -