Estimating the mean of a mark variable under right censoring on the basis of a state function

A mark variable is a generalization of measurements such as lifetime medical costs and quality-adjusted lifetimes. Recently, analysis of the mark variable has generated significant interest as an important component in health treatment evaluation. In this paper, a novel approach to estimating the mean of the mark variable under right censoring is proposed. The proposed estimator is of a much simpler form than most existing estimators advocated in the literature. Theoretical analysis and simulation studies indicate that the proposed estimator has practical applications due to its simplicity and accuracy. A real data set, from a Multicenter Automatic Defibrillator Implantation Trial (MADIT), is used to illustrate the proposed methodology.