Semiparametric bounds on treatment effects

摘要

We present a variety of semiparametric models that produce bounds on the average causal effect of a binary treatment on a binary outcome, the semiparametric assumptions exploit variation in observable covariates to narrow the bounds. In our main model, the outcome is determined by a generalized linear model, but the treatment may be arbitrarily endogenous. Our bounding strategy does not require the existence of an instrument, but incorporating an instrument narrows the bounds. The bounds are furtherimproved by combining the semiparametric model with the joint thresholdnrrossing assumption of Shaikh and Vytlacil (2005).