We develop new quasi-experimental tools to understand algorithmic discrimination and build non-discriminatory algorithms when the outcome of interest is only selectively observed. These tools are applied in the context of pretrial bail decisions, where conventional algorithmic predictions are...

Marginal outcome tests compare the expected effects of a decision on individuals who are of different races but at the same indifference point of the decision-maker. I present a simple formalization of how such tests can detect racial bias, defined as a deviation from accurate statistical...

Lottery estimates suggest oversubscribed urban charter schools boost student achievement markedly. But these estimates needn't capture treatment effects for students who haven't applied to charter schools or for students attending charters for which demand is weak. This paper reports estimates...