Identification and estimation of a triangular model with multiple endogenous variables and insufficiently many instrumental variables

Liquan Huang, Umair Khalil, Neşe Yıldız

Research output: Contribution to journalArticleResearchpeer-review

Abstract

We develop a novel identification method for a partially linear model with multiple endogenous variables of interest but a single instrumental variable, which could even be binary. We present an easy-to-implement consistent estimator for the parametric part. This estimator retains n-convergence rate and asymptotic normality even though we have a generated regressor in our setup. The nonparametric part of the model is also identified. We also outline how our identification strategy can be extended to a fully non-parametric model. Finally, we use our methods to assess the impact of smoking during pregnancy on birth weight.

Original languageEnglish
Pages (from-to)346-366
Number of pages21
JournalJournal of Econometrics
Volume208
Issue number2
DOIs
Publication statusPublished - Feb 2019

Keywords

  • Control function approach
  • Identification
  • Multiple endogenous variables

Cite this

@article{c2d84117c0204f6d83a7e8ae84ef997b,
title = "Identification and estimation of a triangular model with multiple endogenous variables and insufficiently many instrumental variables",
abstract = "We develop a novel identification method for a partially linear model with multiple endogenous variables of interest but a single instrumental variable, which could even be binary. We present an easy-to-implement consistent estimator for the parametric part. This estimator retains n-convergence rate and asymptotic normality even though we have a generated regressor in our setup. The nonparametric part of the model is also identified. We also outline how our identification strategy can be extended to a fully non-parametric model. Finally, we use our methods to assess the impact of smoking during pregnancy on birth weight.",
keywords = "Control function approach, Identification, Multiple endogenous variables",
author = "Liquan Huang and Umair Khalil and Neşe Yıldız",
year = "2019",
month = "2",
doi = "10.1016/j.jeconom.2017.10.009",
language = "English",
volume = "208",
pages = "346--366",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier",
number = "2",

}

Identification and estimation of a triangular model with multiple endogenous variables and insufficiently many instrumental variables. / Huang, Liquan; Khalil, Umair; Yıldız, Neşe.

In: Journal of Econometrics, Vol. 208, No. 2, 02.2019, p. 346-366.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Identification and estimation of a triangular model with multiple endogenous variables and insufficiently many instrumental variables

AU - Huang, Liquan

AU - Khalil, Umair

AU - Yıldız, Neşe

PY - 2019/2

Y1 - 2019/2

N2 - We develop a novel identification method for a partially linear model with multiple endogenous variables of interest but a single instrumental variable, which could even be binary. We present an easy-to-implement consistent estimator for the parametric part. This estimator retains n-convergence rate and asymptotic normality even though we have a generated regressor in our setup. The nonparametric part of the model is also identified. We also outline how our identification strategy can be extended to a fully non-parametric model. Finally, we use our methods to assess the impact of smoking during pregnancy on birth weight.

AB - We develop a novel identification method for a partially linear model with multiple endogenous variables of interest but a single instrumental variable, which could even be binary. We present an easy-to-implement consistent estimator for the parametric part. This estimator retains n-convergence rate and asymptotic normality even though we have a generated regressor in our setup. The nonparametric part of the model is also identified. We also outline how our identification strategy can be extended to a fully non-parametric model. Finally, we use our methods to assess the impact of smoking during pregnancy on birth weight.

KW - Control function approach

KW - Identification

KW - Multiple endogenous variables

UR - http://www.scopus.com/inward/record.url?scp=85057266693&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2017.10.009

DO - 10.1016/j.jeconom.2017.10.009

M3 - Article

VL - 208

SP - 346

EP - 366

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -