Causal mediation analysis in instrumental-variables regressions. (September 2020)

• Record Type: Journal Article
• Authors: Dippel, Christian; Ferrara, Andreas; Heblich, Stephan
• Is Part Of: Stata journal. Volume 20:Number 3(2020)
• Page Start: 613
• Page End: 626
• Publication Date: 2020-09
• Subjects: st0611 -- ivmediate -- causal mediation analysis -- treatment effects -- instrumental variables; Statistics -- Periodicals; Statistics -- Computer programs -- Periodicals; 001.422
• DOI: 10.1177/1536867X20953572
• Languages: English
• ISSNs: 1536-867X

Abstract

In this article, we describe the use ofivmediate, a new command to estimate causal mediation effects in instrumental-variables settings using the framework developed by Dippel et al. (2020, unpublished manuscript).ivmediate allows estimation of a treatment effect and the share of this effect that can be attributed to a mediator variable. While both treatment and mediator can be potentially endogenous, a single instrument suffices to identify both the causal treatment and the mediation effects.