Partial Identification of the Average Treatment Effect Using Instrumental Variables: Review of Methods for Binary Instruments, Treatments, and Outcomes
Several methods have been proposed for partially or point identifying the average treatment effect (ATE) using instrumental variable (IV) type assumptions. The descriptions of these methods are widespread across the statistical, economic, epidemiologic, and computer science literature, and the connections between the methods have not been readily apparent. In the setting of a binary instrument, treatment, and outcome, we review proposed methods for partial and point identification of the ATE under IV assumptions, express the identification results in a common notation and terminology, and propose a taxonomy that is based on sets of identifying assumptions. We further demonstrate and provide software for the application of these methods to estimate bounds. Supplementary materials for this article are available online.
|Keywords||Average treatment effect, Causal graphical model, Instrument, Instrumental variable, Partial identification, Single world intervention graph|
|Persistent URL||dx.doi.org/10.1080/01621459.2018.1434530, hdl.handle.net/1765/109608|
|Journal||American Statistical Association. Journal|
Swanson, S.A. (Sonja A.), Hernán, M.A, Miller, M, Robins, J.M. (James M.), & Richardson, T.S. (Thomas S.). (2018). Partial Identification of the Average Treatment Effect Using Instrumental Variables: Review of Methods for Binary Instruments, Treatments, and Outcomes. American Statistical Association. Journal (Vol. 113, pp. 933–947). doi:10.1080/01621459.2018.1434530