Simple resampling methods for censored regression quantiles

Powell (Journal of Econometrics 25 (1984) 303-325; journal of Econometrics 32 (1986) 143-155) considered censored regression quantile estimators. The asymptotic covariance matrices of his estimators depend on the error densit ies and are therefore difficult to estimate reliably. The difficulty may be avoided by applying the bootstrap method (Hahn, Econometric Theory 11 (199 5) 105-121). Calculation of the estimators, however, requires solving a non smooth and nonconvex minimization problem, resulting in high computational costs in implementing the bootstrap, We propose in this paper computational ly simple resampling methods by convexfying Powell's approach in the resamp ling stage. A major advantage of the new methods is that they can be implem ented by efficient linear programming. Simulation studies show that the met hods are reliable even with moderate sample sizes. (C) 2000 Elsevier Scienc e S.A. All rights reserved. JEL classification: C14; C24.