Methods from causal mediation analysis have generalized the traditional approach to direct and indirect effects in the epidemiologic and social science literature by allowing for interaction and nonlinearities. However, the methods from the causal inference literature have themselves been subject to a major limitation, in that the so-called natural direct and indirect effects that are used are not identified from data whenever there is a mediator-outcome confounder that is also affected by the exposure. In this article, we describe three alternative approaches to effect decomposition that give quantities that can be interpreted as direct and indirect effects and that can be identified from data even in the presence of an exposure-induced mediator-outcome confounder. We describe a simple weighting-based estimation method for each of these three approaches, illustrated with data from perinatal epidemiology. The methods described here can shed insight into pathways and questions of mediation even when an exposure-induced mediator-outcome confounder is present.
Supplemental Digital Content is available in the text.
From the aDepartments of Epidemiology and Biostatistics, Harvard School of Public Health, Boston, MA; and bDepartment of Applied Mathematics, Computer Science, and Statistics, University of Ghent, Ghent, Belgium.
T.J.V. was supported by National Institutes of Health grant ES017876. S.V. was supported by Flemish Research Council (FWO Grant G.0111.12).
Supplemental digital content is available through direct URL citations in the HTML and PDF versions of this article (www.epidem.com). This content is not peer-reviewed or copy-edited; it is the sole responsibility of the author.
Correspondence: Tyler J. VanderWeele, Departments of Epidemiology and Biostatistics, Harvard School of Public Health, 677 Huntington Avenue, Boston, MA 02115. E-mail: email@example.com.