We consider the problem of assessing the effects of a treatment on duration outcomes using data from a randomized evaluation with noncompliance. For such settings, we derive nonparametric sharp bounds for average and quantile treatment effects addressing three pervasive problems simultaneously:...

We consider the problem of assessing the effects of a treatment on duration outcomes using data from a randomized evaluation with noncompliance. For such settings, we derive nonparametric sharp bounds for average and quantile treatment effects addressing three pervasive problems simultaneously:...

Researchers often identify degree effects by including degree attainment (D) and years of schooling (S) in a wage model, yet the source of independent variation in these measures is not well understood. We argue that S is negatively correlated with ability among degree-holders because the most...

Researchers often identify degree effects by including degree attainment (D) and years of schooling (S) in a wage model, yet the source of independent variation in these measures is not well understood. We argue that S is negatively correlated with ability among degree-holders because the most...

Researchers often identify degree effects by including degree attainment (D) and years of schooling (S) in a wage model, yet the source of independent variation in these measures is not well understood. We argue that S is negatively correlated with ability among degree-holders because the most...

Most of the literature on the evaluation of training programs focuses on the effect of participation on a particular outcome (e.g. earnings). The "treatment" is generally represented by a binary variable equal to one if participation in the program occurs, and equal to zero if no participation...

Most of the literature on the evaluation of training programs focuses on the effect of participation on a particular outcome (e.g. earnings). The "treatment" is generally represented by a binary variable equal to one if participation in the program occurs, and equal to zero if no participation...