Proxy Controls and Panel Data

Abstract

We provide new results for nonparametric identification, estimation, and inference of causal effects using `proxy controls': observables that are noisy but informative proxies for unobserved confounding factors. Our analysis applies to cross-sectional settings but is particularly well-suited to panel models. Our identification results motivate a simple and `well-posed' nonparametric estimator. We derive convergence rates for the estimator and construct uniform confidence bands with asymptotically correct size. In panel settings, our methods provide a novel approach to the difficult problem of identification with non-separable, general heterogeneity and fixed $T$. In panels, observations from different periods serve as proxies for unobserved heterogeneity and our key identifying assumptions follow from restrictions on the serial dependence structure. We apply our methods to two empirical settings. We estimate consumer demand counterfactuals using panel data and we estimate causal effects of grade retention on cognitive performance.