Inference with Cluster Imbalance: The Case of State Corporate Laws

Harvard Law School John M. Olin Center Discussion Paper No. 1024 (2019)

European Corporate Governance Institute – Finance Working Paper No. 644/2019

34 Pages Posted: 17 Dec 2019 Last revised: 28 Dec 2023

See all articles by Allen Hu

Allen Hu

Yale School of Management

Holger Spamann

Harvard Law School; ECGI

Date Written: December 28, 2020

Abstract

A workhorse research design identifies the effects of corporate governance by changes in state laws, clustering standard errors by state of incorporation. Asymptotic inference using these standard errors, however, dramatically understates false positives: in a typical specification, randomly generated placebo laws have 1/5/10%-level significant estimated treatment effects 9/21/30% of the time. This poor finite sample performance is due to unequal cluster sizes, especially Delaware's concentration of half of all incorporations. Bootstrap or permutation tests mostly fix the problem, common robustness checks less so. The placebo law approach can also be used to calculate power, which will be acceptably high only for substantial effect sizes.

Keywords: Anti-Takeover Laws, Corporate Governance, Cluster-Robust Inference, Monte Carlo, Placebo Laws, Permutation Test

JEL Classification: C12, G34, G38, K22

Suggested Citation

Hu, Allen and Spamann, Holger, Inference with Cluster Imbalance: The Case of State Corporate Laws (December 28, 2020). Harvard Law School John M. Olin Center Discussion Paper No. 1024 (2019), European Corporate Governance Institute – Finance Working Paper No. 644/2019, Available at SSRN: https://ssrn.com/abstract=3499101 or http://dx.doi.org/10.2139/ssrn.3499101

Allen Hu

Yale School of Management ( email )

165 Whitney Ave
New Haven, CT 06511

HOME PAGE: http://www.anallenhu.com

Holger Spamann (Contact Author)

Harvard Law School ( email )

Cambridge, MA 02138
United States

ECGI ( email )

c/o the Royal Academies of Belgium
Rue Ducale 1 Hertogsstraat
1000 Brussels
Belgium

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
414
Abstract Views
2,727
Rank
130,013
PlumX Metrics