Nonparametric Inference for the Proportionality Function in the Random Censorship Model

Abstract

Censorship in the random censorship model is described by a pro-portionality function (t), where (t) is a function of the survival function S T of the lifetimes, and the survival function S C of the censoring times. An estimator of (t) is proposed and asymptotic properties of the estimator are ascertained. A conndence band for (t) using the bootstrap is derived. We also develop a bootstrap test of H 0 :(t)=, where the constant value of is unspeciied. The results are applied to an actual dataset.

Cite this paper

@inproceedings{Hollander2000NonparametricIF, title={Nonparametric Inference for the Proportionality Function in the Random Censorship Model}, author={Myles Hollander and Glen Laird and Kai-Sheng Song}, year={2000} }