Are two-way fixed-effect difference-in-differences estimates blowing smoke? A cautionary tale from state-level bank branching deregulation

41 Pages Posted: 6 Jul 2021 Last revised: 6 Dec 2021

See all articles by Anthony Zdrojewski

Anthony Zdrojewski

Rice University

Alexander W. Butler

Rice University - Jesse H. Jones Graduate School of Business

Date Written: November 15, 2021

Abstract

We illustrate the sensitivity of two-way fixed effects difference-indifferences estimates to innocuous changes in data structure. Using the staggered rollout of state-level bank branching deregulations,
three outcome variables are brought to bear on the interventions: personal income growth (a replication), house prices (new to the literature), and per capita cigarette purchases (a falsification test). Estimates are sensitive to panel length, and the data structure creates the false impression of a causal effect of the interventions on all three outcome variables. We contend that any two-way fixed effects regression using this set of interventions is at risk of generating spurious results.

Keywords: banking, deregulation, economic growth, difference-in-differences, two-way fixed effect estimation

JEL Classification: C13, C18, C23, G21, G28, O47

Suggested Citation

Zdrojewski, Anthony and Butler, Alexander W., Are two-way fixed-effect difference-in-differences estimates blowing smoke? A cautionary tale from state-level bank branching deregulation (November 15, 2021). Available at SSRN: https://ssrn.com/abstract=3871311 or http://dx.doi.org/10.2139/ssrn.3871311

Anthony Zdrojewski

Rice University ( email )

6100 South Main Street
Houston, TX 77005-1892
United States

Alexander W. Butler (Contact Author)

Rice University - Jesse H. Jones Graduate School of Business ( email )

MS 531
Houston, TX 77005
United States
713-348-6341 (Phone)

HOME PAGE: http://www.owlnet.rice.edu/~awbutler/

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
164
Abstract Views
616
Rank
272,771
PlumX Metrics