On the instrument functional form with a binary endogenous explanatory variable

Ruonan Xu

doi:10.1016/j.econlet.2021.109993

On the instrument functional form with a binary endogenous explanatory variable

Ruonan Xu

School of Arts and Sciences, Economics

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

19 Scopus citations

Abstract

I demonstrate that, in a linear regression model with a binary endogenous explanatory variable, a two-step IV estimation procedure could avoid the weak identification issue caused by a first-stage linear projection onto the linear instruments.

Original language	English (US)
Article number	109993
Journal	Economics Letters
Volume	206
DOIs	https://doi.org/10.1016/j.econlet.2021.109993
State	Published - Sep 2021

All Science Journal Classification (ASJC) codes

Finance
Economics and Econometrics

Keywords

F statistic
Fitted probit probability
Heteroskedasticity
Two-stage least squares
Weak instruments

Access to Document

10.1016/j.econlet.2021.109993

Cite this

@article{d92dc3a304fa4706bdc44d652038497a,

title = "On the instrument functional form with a binary endogenous explanatory variable",

abstract = "I demonstrate that, in a linear regression model with a binary endogenous explanatory variable, a two-step IV estimation procedure could avoid the weak identification issue caused by a first-stage linear projection onto the linear instruments.",

keywords = "F statistic, Fitted probit probability, Heteroskedasticity, Two-stage least squares, Weak instruments",

author = "Ruonan Xu",

note = "Publisher Copyright: {\textcopyright} 2021",

year = "2021",

month = sep,

doi = "10.1016/j.econlet.2021.109993",

language = "English (US)",

volume = "206",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - On the instrument functional form with a binary endogenous explanatory variable

AU - Xu, Ruonan

PY - 2021/9

Y1 - 2021/9

N2 - I demonstrate that, in a linear regression model with a binary endogenous explanatory variable, a two-step IV estimation procedure could avoid the weak identification issue caused by a first-stage linear projection onto the linear instruments.

AB - I demonstrate that, in a linear regression model with a binary endogenous explanatory variable, a two-step IV estimation procedure could avoid the weak identification issue caused by a first-stage linear projection onto the linear instruments.

KW - F statistic

KW - Fitted probit probability

KW - Heteroskedasticity

KW - Two-stage least squares

KW - Weak instruments

UR - http://www.scopus.com/inward/record.url?scp=85109917893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85109917893&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2021.109993

DO - 10.1016/j.econlet.2021.109993

M3 - Article

AN - SCOPUS:85109917893

SN - 0165-1765

VL - 206

JO - Economics Letters

JF - Economics Letters

M1 - 109993

ER -

On the instrument functional form with a binary endogenous explanatory variable

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this