Code for: Judging Judge Fixed Effects

We propose a test for the identifying assumptions invoked in designs based on the random assignment of cases to judges. The standard identifying assumptions of exclusion and monotonicity imply that the conditional expectation of the outcome given the assigned judge's propensity to treat is a continuous function with bounded slope. We develop a nonparametric test of this restriction, show its asymptotic validity, and demonstrate its finite-sample performance in simulations. We apply our test in an empirical setting from the literature examining the effects of pre-trial detention on defendant outcomes in New York. When the assumptions are not satisfied, we propose weaker versions of the usual exclusion and monotonicity restrictions under which the IV estimator still converges to a proper weighted average of treatment effects.