Estimating a nonparametric triangular model with binary endogenous regressors

Research output: Contribution to journalArticle

Abstract

We consider identification and estimation in a nonparametric triangular system with a binary endogenous regressor and nonseparable errors. For identification, we take a control function approach utilizing the Dynkin system idea. We articulate various trade-offs, including continuity, monotonicity and differentiability. For estimation, we use the idea of local instruments under smoothness assumptions, but we do not assume additive separability in latent variables. Our estimator uses nonparametric kernel regression techniques and its statistical properties are derived using the functional delta method. We establish that it is n2/7 -consistent and has a limiting normal distribution. We apply the method to estimate the returns on a college education. Unlike existing work, we find that returns on a college education are consistently positive. Moreover, the returns curves we estimate are inconsistent with the shape restrictions imposed in those papers.

Original languageEnglish (US)
Pages (from-to)113-149
Number of pages37
JournalEconometrics Journal
Volume19
Issue number2
DOIs
StatePublished - Jun 1 2016

Fingerprint

Endogenous regressors
Education
Separability
Trade-offs
Differentiability
Delta method
Latent variables
Continuity
Normal distribution
Kernel regression
Monotonicity
Control function
Estimator

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

@article{fb9a525cc2924abc86ca85b9bd055dd2,
title = "Estimating a nonparametric triangular model with binary endogenous regressors",
abstract = "We consider identification and estimation in a nonparametric triangular system with a binary endogenous regressor and nonseparable errors. For identification, we take a control function approach utilizing the Dynkin system idea. We articulate various trade-offs, including continuity, monotonicity and differentiability. For estimation, we use the idea of local instruments under smoothness assumptions, but we do not assume additive separability in latent variables. Our estimator uses nonparametric kernel regression techniques and its statistical properties are derived using the functional delta method. We establish that it is n2/7 -consistent and has a limiting normal distribution. We apply the method to estimate the returns on a college education. Unlike existing work, we find that returns on a college education are consistently positive. Moreover, the returns curves we estimate are inconsistent with the shape restrictions imposed in those papers.",
author = "Jun, {Sung Jae} and Joris Pinkse and Haiqing Xu",
year = "2016",
month = "6",
day = "1",
doi = "10.1111/ectj.12066",
language = "English (US)",
volume = "19",
pages = "113--149",
journal = "Econometrics Journal",
issn = "1368-4221",
publisher = "Wiley-Blackwell",
number = "2",

}

Estimating a nonparametric triangular model with binary endogenous regressors. / Jun, Sung Jae; Pinkse, Joris; Xu, Haiqing.

In: Econometrics Journal, Vol. 19, No. 2, 01.06.2016, p. 113-149.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Estimating a nonparametric triangular model with binary endogenous regressors

AU - Jun, Sung Jae

AU - Pinkse, Joris

AU - Xu, Haiqing

PY - 2016/6/1

Y1 - 2016/6/1

N2 - We consider identification and estimation in a nonparametric triangular system with a binary endogenous regressor and nonseparable errors. For identification, we take a control function approach utilizing the Dynkin system idea. We articulate various trade-offs, including continuity, monotonicity and differentiability. For estimation, we use the idea of local instruments under smoothness assumptions, but we do not assume additive separability in latent variables. Our estimator uses nonparametric kernel regression techniques and its statistical properties are derived using the functional delta method. We establish that it is n2/7 -consistent and has a limiting normal distribution. We apply the method to estimate the returns on a college education. Unlike existing work, we find that returns on a college education are consistently positive. Moreover, the returns curves we estimate are inconsistent with the shape restrictions imposed in those papers.

AB - We consider identification and estimation in a nonparametric triangular system with a binary endogenous regressor and nonseparable errors. For identification, we take a control function approach utilizing the Dynkin system idea. We articulate various trade-offs, including continuity, monotonicity and differentiability. For estimation, we use the idea of local instruments under smoothness assumptions, but we do not assume additive separability in latent variables. Our estimator uses nonparametric kernel regression techniques and its statistical properties are derived using the functional delta method. We establish that it is n2/7 -consistent and has a limiting normal distribution. We apply the method to estimate the returns on a college education. Unlike existing work, we find that returns on a college education are consistently positive. Moreover, the returns curves we estimate are inconsistent with the shape restrictions imposed in those papers.

UR - http://www.scopus.com/inward/record.url?scp=84990195583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84990195583&partnerID=8YFLogxK

U2 - 10.1111/ectj.12066

DO - 10.1111/ectj.12066

M3 - Article

VL - 19

SP - 113

EP - 149

JO - Econometrics Journal

JF - Econometrics Journal

SN - 1368-4221

IS - 2

ER -