Estimation of the Bivariate and Marginal Distributions with Censored Data.

摘要

Two new estimators for the bivariate distribution when both variables are subject to censoring are proposed. One of the estimators is valid under the assumption that the censoring variables are independent from the variables of interest, and leads to an estimator of the marginal distribution that out performs the Kaplan-Meier estimator. The other assumes only that one of the censoring variables is conditionally independent of the survival time it censors given the other survival time. Both estimators require estimation of the conditional distribution when the conditioning variable is subject to censoring. Such a method of estimation is proposed. The weak convergence of the proposed estimators is obtained. Simulation results suggest that they perform well relative to existing estimators.