對於隨機設限資料,Satten和Datta (2001)證明Kaplan-Meier估計值可以表示成以設限時間機率分配為權數的加權平均值。本文中,我們證明截取資料下,Lynden-Bell(1971)所提出的product-limit估計值亦可表示成以截取時間機率分配為權數的加權平均值。
For randomly censored data, Satten and Datta (2001) showed that the Kaplan-Meier estimator can be expressed as an inverse-probability-of censoring weighted estimator. In this article, it is shown that the truncation product-limit estimate, first introduced by Lynden-Bell(1971), can also be expressed as an inverse-probability-of truncation weighted average, where the weights are related to the distribution function of truncation variables.