One Instrument to Rule Them All: The Bias and Coverage of Just-ID IV

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Angrist, Joshua, Kolesár, Michal
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909442472148992
author Angrist, Joshua
Kolesár, Michal
author_facet Angrist, Joshua
Kolesár, Michal
contents We revisit the finite-sample behavior of single-variable just-identified instrumental variables (just-ID IV) estimators, arguing that in most microeconometric applications, the usual inference strategies are likely reliable. Three widely-cited applications are used to explain why this is so. We then consider pretesting strategies of the form $t_{1}>c$, where $t_{1}$ is the first-stage $t$-statistic, and the first-stage sign is given. Although pervasive in empirical practice, pretesting on the first-stage $F$-statistic exacerbates bias and distorts inference. We show, however, that median bias is both minimized and roughly halved by setting $c=0$, that is by screening on the sign of the \textit{estimated} first stage. This bias reduction is a free lunch: conventional confidence interval coverage is unchanged by screening on the estimated first-stage sign. To the extent that IV analysts sign-screen already, these results strengthen the case for a sanguine view of the finite-sample behavior of just-ID IV.
format Preprint
id arxiv_https___arxiv_org_abs_2110_10556
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle One Instrument to Rule Them All: The Bias and Coverage of Just-ID IV
Angrist, Joshua
Kolesár, Michal
Econometrics
Methodology
We revisit the finite-sample behavior of single-variable just-identified instrumental variables (just-ID IV) estimators, arguing that in most microeconometric applications, the usual inference strategies are likely reliable. Three widely-cited applications are used to explain why this is so. We then consider pretesting strategies of the form $t_{1}>c$, where $t_{1}$ is the first-stage $t$-statistic, and the first-stage sign is given. Although pervasive in empirical practice, pretesting on the first-stage $F$-statistic exacerbates bias and distorts inference. We show, however, that median bias is both minimized and roughly halved by setting $c=0$, that is by screening on the sign of the \textit{estimated} first stage. This bias reduction is a free lunch: conventional confidence interval coverage is unchanged by screening on the estimated first-stage sign. To the extent that IV analysts sign-screen already, these results strengthen the case for a sanguine view of the finite-sample behavior of just-ID IV.
title One Instrument to Rule Them All: The Bias and Coverage of Just-ID IV
topic Econometrics
Methodology
url https://arxiv.org/abs/2110.10556