Consistent estimation of linear regression models using matched data

Standard

Consistent estimation of linear regression models using matched data. / Hirukawa, Masayuki; Prokhorov, Artem.

In: Journal of Econometrics, Vol. 203, No. 2, 01.04.2018, p. 344-358.

Research output: Contribution to journal › Article › peer-review

Author

Hirukawa, Masayuki ; Prokhorov, Artem. / Consistent estimation of linear regression models using matched data. In: Journal of Econometrics. 2018 ; Vol. 203, No. 2. pp. 344-358.

BibTeX

@article{120b3e890df14149b42f88a18d67ccd3,

title = "Consistent estimation of linear regression models using matched data",

abstract = "Economists often use matched samples, especially when dealing with earnings data where a number of missing observations need to be imputed. In this paper, we demonstrate that the ordinary least squares estimator of the linear regression model using matched samples is inconsistent and has a non-standard convergence rate to its probability limit. If only a few variables are used to impute the missing data, then it is possible to correct for the bias. We propose two semiparametric bias-corrected estimators and explore their asymptotic properties. The estimators have an indirect-inference interpretation, and they attain the parametric convergence rate when the number of matching variables is no greater than four. Monte Carlo simulations confirm that the bias correction works very well in such cases.",

keywords = "Bias correction, Indirect inference, Linear regression, Matching estimation, Measurement error bias, PROPENSITY SCORE, EARNINGS IMPUTATION, INSTRUMENTAL VARIABLES, BIAS, NEAREST-NEIGHBOR IMPUTATION, EDUCATIONAL-ATTAINMENT, SAMPLE PROPERTIES, DATA SETS, CONSUMPTION, MOMENTS",

author = "Masayuki Hirukawa and Artem Prokhorov",

year = "2018",

month = apr,

day = "1",

doi = "10.1016/j.jeconom.2017.07.006",

language = "English",

volume = "203",

pages = "344--358",

journal = "Journal of Econometrics",

issn = "0304-4076",

publisher = "Elsevier",

number = "2",

}

RIS

TY - JOUR

T1 - Consistent estimation of linear regression models using matched data

AU - Hirukawa, Masayuki

AU - Prokhorov, Artem

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Economists often use matched samples, especially when dealing with earnings data where a number of missing observations need to be imputed. In this paper, we demonstrate that the ordinary least squares estimator of the linear regression model using matched samples is inconsistent and has a non-standard convergence rate to its probability limit. If only a few variables are used to impute the missing data, then it is possible to correct for the bias. We propose two semiparametric bias-corrected estimators and explore their asymptotic properties. The estimators have an indirect-inference interpretation, and they attain the parametric convergence rate when the number of matching variables is no greater than four. Monte Carlo simulations confirm that the bias correction works very well in such cases.

AB - Economists often use matched samples, especially when dealing with earnings data where a number of missing observations need to be imputed. In this paper, we demonstrate that the ordinary least squares estimator of the linear regression model using matched samples is inconsistent and has a non-standard convergence rate to its probability limit. If only a few variables are used to impute the missing data, then it is possible to correct for the bias. We propose two semiparametric bias-corrected estimators and explore their asymptotic properties. The estimators have an indirect-inference interpretation, and they attain the parametric convergence rate when the number of matching variables is no greater than four. Monte Carlo simulations confirm that the bias correction works very well in such cases.

KW - Bias correction

KW - Indirect inference

KW - Linear regression

KW - Matching estimation

KW - Measurement error bias

KW - PROPENSITY SCORE

KW - EARNINGS IMPUTATION

KW - INSTRUMENTAL VARIABLES

KW - BIAS

KW - NEAREST-NEIGHBOR IMPUTATION

KW - EDUCATIONAL-ATTAINMENT

KW - SAMPLE PROPERTIES

KW - DATA SETS

KW - CONSUMPTION

KW - MOMENTS

UR - http://www.scopus.com/inward/record.url?scp=85041572719&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2017.07.006

DO - 10.1016/j.jeconom.2017.07.006

M3 - Article

AN - SCOPUS:85041572719

VL - 203

SP - 344

EP - 358

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -

ID: 36345117