Non-parametric estimation for the location of a change-point in an otherwise smooth hazard function under random censoring

A non-parametric wavelet based estimator is proposed for the location of a change-point in an otherwise smooth hazard function under non-informative r andom right censoring. The proposed estimator is based on wavelet coefficie nts differences via an appropriate parametrization of the time-frequency pl ane. The study of the estimator is facilitated by the strong representation theorem for the Kaplan-Meier estimator established by Lo and Singh (1986). The performance of the estimator is checked via simulations and two real e xamples conclude the paper.