American Political Science Review

Research Article

Unpacking the Black Box of Causality: Learning about Causal Mechanisms from Experimental and Observational Studies

KOSUKE IMAIa1 c1, LUKE KEELEa2 c2, DUSTIN TINGLEYa3 c3 and TEPPEI YAMAMOTOa4 c4

a1 Princeton University

a2 Pennsylvania State University

a3 Harvard University

a4 Massachusetts Institute of Technology

Abstract

Identifying causal mechanisms is a fundamental goal of social science. Researchers seek to study not only whether one variable affects another but also how such a causal relationship arises. Yet commonly used statistical methods for identifying causal mechanisms rely upon untestable assumptions and are often inappropriate even under those assumptions. Randomizing treatment and intermediate variables is also insufficient. Despite these difficulties, the study of causal mechanisms is too important to abandon. We make three contributions to improve research on causal mechanisms. First, we present a minimum set of assumptions required under standard designs of experimental and observational studies and develop a general algorithm for estimating causal mediation effects. Second, we provide a method for assessing the sensitivity of conclusions to potential violations of a key assumption. Third, we offer alternative research designs for identifying causal mechanisms under weaker assumptions. The proposed approach is illustrated using media framing experiments and incumbency advantage studies.

(Online publication November 10 2011)

Correspondence:

c1 Kosuke Imai is Associate Professor, Department of Politics, Princeton University, Corwin Hall 036, Princeton NJ 08544 (kimai@princeton.edu).

c2 Luke Keele is Assistant Professor, Department of Political Science, Pennsylvania State University, 211 Pond Lab, University Park, PA 16802 (ljk20@psu.edu).

c3 Dustin Tingley is Assistant Professor, Department of Government, Harvard University, 1737 Cambridge Street, CGIS Knafel Building 208, Cambridge MA 02138 (dtingley@gov.harvard.edu).

c4 Teppei Yamamoto is Assistant Professor, Department of Political Science, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139 (teppei@mit.edu).

Footnotes

The companion articles that present technical aspects of the methods introduced here are available as Imai, Keele, and Tingley (2010), and Imai, Keele, Tingley, and Yamamoto (2010, 2011). All of our proposed methods can be implemented via an R package, mediation (Imai et al. 2010), which is freely available for download at the Comprehensive R Archive Network (http://cran.r-project.org/web/packages/mediation). A Stata package mediation by Raymond Hicks and Tingley is available at IDEAS (http://ideas.repec.org/c/boc/bocode/s457294.html). The replication archive for this article is available as Imai et al. (2011). We thank Ted Brader, Gary Jacobson, and Jonathan Katz for providing us with their data. We also thank Christina Davis, Michael Donnelly, Kevin Esterling, Marty Gilens, Don Green, Simon Jackman, Gary King, Arthur Lupia, Rose McDermott, Tali Mendelberg, Marcus Prior, Cesar Zucco, and participants at the West Coast Experiment Conference, the NSF Conference on Politics Experiments, and the Institute of Statistical Mathematics Summer Lecture Series, as well as seminar participants at Northwestern University and the University of Chicago for helpful suggestions. Comments from an APSR co-editor and three anonymous reviewers significantly improved the presentation of this article. Imai acknowledges financial support from the National Science Foundation (SES-0849715 and SES-0918968).

Metrics