Enough Already About 'Black Box' Experiments: Studying Mediation is More Difficult than Most Scholars Suppose

Annals of the American Academy of Political and Social Science, Vol. 628, pp. 200-08, March 2010

18 Pages Posted: 2 Feb 2010 Last revised: 21 May 2010

Donald P. Green

Columbia University - Department of Political Science

Shang E. Ha

Brooklyn College - CUNY

John G. Bullock

University of Texas at Austin

Date Written: May 1, 2009

Abstract

Recent years have seen growing enthusiasm for regression models that purport to establish claims about mediation. Despite their growing popularity, these regression models rest on naive assumptions. The point of this essay is to puncture the widely held view that it is a relatively simple matter to establish the mechanism by which causality is transmitted. This means puncturing the faith that has been placed in commonly used statistical methods of establishing mediation.

Keywords: Mediation, Experiments, Causal Inference, Indirect Effects

JEL Classification: C90

Suggested Citation

Green, Donald P. and Ha, Shang E. and Bullock, John G., Enough Already About 'Black Box' Experiments: Studying Mediation is More Difficult than Most Scholars Suppose (May 1, 2009). Annals of the American Academy of Political and Social Science, Vol. 628, pp. 200-08, March 2010. Available at SSRN: https://ssrn.com/abstract=1544416

Donald P. Green (Contact Author)

Columbia University - Department of Political Science ( email )

7th Floor, International Affairs Bldg.
420 W. 118th Street
New York, NY 10027
United States

Shang E. Ha

Brooklyn College - CUNY ( email )

2900 Bedford Avenue
Brooklyn, NY 11210
United States

John G. Bullock

University of Texas at Austin ( email )

Austin, TX 78712
United States

Paper statistics

Downloads
521
Rank
41,051
Abstract Views
2,637