Saved in:
Bibliographic Details
Main Authors: Argañaraz, Facundo, de Chaisemartin, Clément, Lei, Ziteng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.03208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909673603465216
author Argañaraz, Facundo
de Chaisemartin, Clément
Lei, Ziteng
author_facet Argañaraz, Facundo
de Chaisemartin, Clément
Lei, Ziteng
contents We consider treatment-effect estimation using a first-difference regression of an outcome evolution $ΔY$ on a treatment evolution $ΔD$. Under a causal model in levels with a time-varying effect, the regression residual is a function of the period-one treatment $D_{1}$. Then, researchers should test if $ΔD$ and $D_{1}$ are correlated: if they are, the regression may suffer from an omitted variable bias. To solve it, researchers may control nonparametrically for $E(ΔD|D_{1})$. We use our results to revisit first-difference regressions estimated on the data of \cite{acemoglu2016import}, who study the effect of imports from China on US employment. $ΔD$ and $D_{1}$ are strongly correlated, thus implying that first-difference regressions may be biased if the effect of Chinese imports changes over time. The coefficient on $ΔD$ is no longer significant when controlling for $E(ΔD|D_{1})$.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03208
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Randomly Assigned First Differences?
Argañaraz, Facundo
de Chaisemartin, Clément
Lei, Ziteng
Econometrics
We consider treatment-effect estimation using a first-difference regression of an outcome evolution $ΔY$ on a treatment evolution $ΔD$. Under a causal model in levels with a time-varying effect, the regression residual is a function of the period-one treatment $D_{1}$. Then, researchers should test if $ΔD$ and $D_{1}$ are correlated: if they are, the regression may suffer from an omitted variable bias. To solve it, researchers may control nonparametrically for $E(ΔD|D_{1})$. We use our results to revisit first-difference regressions estimated on the data of \cite{acemoglu2016import}, who study the effect of imports from China on US employment. $ΔD$ and $D_{1}$ are strongly correlated, thus implying that first-difference regressions may be biased if the effect of Chinese imports changes over time. The coefficient on $ΔD$ is no longer significant when controlling for $E(ΔD|D_{1})$.
title Randomly Assigned First Differences?
topic Econometrics
url https://arxiv.org/abs/2411.03208