Bounded, efficient and multiply robust estimation of average treatment effects using instrumental variables. (18th December 2017)

• Record Type: Journal Article
• Authors: Wang, Linbo; Tchetgen Tchetgen, Eric
• Is Part Of: Journal of the Royal Statistical Society. Volume 80:Number 3(2018)
• Page Start: 531
• Page End: 550
• Publication Date: 2017-12-18
• Subjects: Binary outcome -- Causal inference -- Identification -- Semiparametric inference -- Unmeasured confounding; Statistics -- Periodicals; Great Britain -- Statistics -- Periodicals; 519.2
• DOI: 10.1111/rssb.12262
• Languages: English
• ISSNs: 1369-7412

Abstract

Summary: Instrumental variables are widely used for estimating causal effects in the presence of unmeasured confounding. Under the standard instrumental variable model, however, the average treatment effect is only partially identifiable. To address this, we propose novel assumptions that enable identification of the average treatment effect. Our identification assumptions are clearly separated from model assumptions that are needed for estimation, so researchers are not required to commit to a specific observed data model in establishing identification. We then construct multiple estimators that are consistent under three different observed data models, and multiply robust estimators that are consistent in the union of these observed data models. We pay special attention to the case of binary outcomes, for which we obtain bounded estimators of the average treatment effect that are guaranteed to lie between −1 and 1. Our approaches are illustrated with simulations and a data analysis evaluating the causal effect of education on earnings.