Treatment Effects With Censoring and Endogeneity

This paper develops a nonparametric approach to identification and estimation of treatment effects on censored outcomes when treatment may be endogenous and have arbitrarily heterogeneous effects. Identification is based on an instrumental variable that satisfies the exclusion and monotonicity conditions standard in the local average treatment effects framework. The paper proposes a censored quantile treatment effects estimator, derives its asymptotic distribution, and illustrates its performance using Monte Carlo simulations. Even in the exogenous case, the estimator performs better in finite samples than existing censored quantile regression estimators, and performs nearly as well as maximum likelihood estimators in cases where their distributional assumptions hold. An empirical application to a subsidized job training program finds that participation significantly and dramatically reduced the duration of jobless spells, especially at the right tail of the distribution. keywords: quantile regression, survival analysis, duration data, instrumental variables, local average treatment effects