Download this Paper Open PDF in Browser

Misunderstandings among Experimentalists and Observationalists about Causal Inference

Journal of the Royal Statistical Society, Series A, Forthcoming

30 Pages Posted: 20 Dec 2007  

Kosuke Imai

Princeton University - Department of Political Science

Gary King

Harvard University

Elizabeth A. Stuart

Johns Hopkins Bloomberg School of Public Health

Abstract

We attempt to clarify, and show how to avoid, several fallacies of causal inference in experimental and observational studies. These fallacies concern hypothesis tests for covariate balance between the treated and control groups, and the consequences of using randomization, blocking before randomization, and matching after treatment assignment to achieve balance. Applied researchers in a wide range of scientific disciplines seem to fall prey to one or more of these fallacies. To clarify these points, we derive a new three-part decomposition of the potential estimation errors in making causal inferences. We then show how this decomposition can help scholars from different experimental and observational research traditions better understand each other's inferential problems and attempted solutions. We illustrate with a discussion of the misleading conclusions researchers produce when using hypothesis tests to check for balance in experiments and observational studies.

Keywords: average treatment effects, blocking, covariate balance, matching, observational studies

Suggested Citation

Imai, Kosuke and King, Gary and Stuart, Elizabeth A., Misunderstandings among Experimentalists and Observationalists about Causal Inference. Journal of the Royal Statistical Society, Series A, Forthcoming. Available at SSRN: https://ssrn.com/abstract=1013351

Kosuke Imai (Contact Author)

Princeton University - Department of Political Science ( email )

Corwin Hall
Princeton, NJ 08544-1012
United States

Gary King

Harvard University ( email )

1737 Cambridge St.
Institute for Quantitative Social Science
Cambridge, MA 02138
United States
617-500-7570 (Phone)

HOME PAGE: http://gking.harvard.edu

Elizabeth Stuart

Johns Hopkins Bloomberg School of Public Health ( email )

615 North Wolfe Street
Baltimore, MD 21205
United States

HOME PAGE: http://www.biostat.jhsph.edu/~estuart

Paper statistics

Downloads
304
Rank
84,171
Abstract Views
1,228