TY  - RPRT
        AU  - Luna, Xavier de
AU  - Fowler, Philip
AU  - Johansson, Per
        TI  - Proxy Variables and Nonparametric Identification of Causal Effects
        PY  - 2016/Jul/
        PB  - Institute of Labor Economics (IZA)
        CY  - Bonn
        T2  - IZA Discussion Paper
        IS  - 10057
        UR  - https://www.iza.org/publications/dp10057
        AB  - Proxy variables are often used in linear regression models with the aim of removing potential confounding bias. In this paper we formalise proxy variables within the potential outcome framework, giving conditions under which it can be shown that causal effects are nonparametrically identified. We characterise two types of proxy variables and give concrete examples where the proxy conditions introduced may hold by design.
        KW  - potential outcomes
KW  - observational studies
KW  - average treatment effect
KW  - unobserved confounders
        ER  -