I thank Will Bullock, Bob Erikson, Adam Glynn, Kosuke Imai, Luke Keele, John Londregan, Nolan McCarty, Judea Pearl, and Dustin Tingley for their helpful comments, and Kevin Milligan, Enrico Moretti, and Phil Oreopoulos for generously providing their data. I am also grateful to the four anonymous reviewers whose suggestions have significantly improved the manuscript. An earlier version of this article was presented at the 2009 annual meeting of the American Political Science Association, the 2010 annual meeting of the Midwest Political Science Association, and the Third New Faces in Political Methodology Conference at Penn State. Replication materials for the empirical analysis in this article are available electronically as Yamamoto (2011) on the Dataverse Network.
Understanding the Past: Statistical Analysis of Causal Attribution
Article first published online: 13 OCT 2011
© 2011, Midwest Political Science Association
American Journal of Political Science
Volume 56, Issue 1, pages 237–256, January 2012
How to Cite
Yamamoto, T. (2012), Understanding the Past: Statistical Analysis of Causal Attribution. American Journal of Political Science, 56: 237–256. doi: 10.1111/j.1540-5907.2011.00539.x
- Issue published online: 17 JAN 2012
- Article first published online: 13 OCT 2011
Would the third-wave democracies have been democratized without prior modernization? What proportion of the past militarized disputes between nondemocracies would have been prevented had those dyads been democratic? Although political scientists often ask these questions of causal attribution, existing quantitative methods fail to address them. This article proposes an alternative statistical methodology based on the widely accepted counterfactual framework of causal inference. The contribution of this article is threefold. First, it clarifies differences between causal attribution and causal effects by specifying the type of research questions to which each quantity is relevant. Second, it provides a clear resolution of the long-standing methodological debate on “selection on the dependent variable.” Third, the article derives new nonparametric identification results, showing that the complier probability of causal attribution can be identified using an instrumental variable. The proposed framework is illustrated via empirical examples from three subfields of political science.