分层部分样本轮换抽样下的混合估计

An Idea on the Handling of Zero Failure Data

在实际抽样调查中，人们常采用部分样本轮换的方式进行抽样调查，然而，它的估计与精度如何，尚未见报导．本文试图对常用的分层抽样方式下的部分样本轮换抽样的估计及其精度问题作一探讨：给出了一个最佳的混合估计方法；讨论了部分样本轮换抽样的数目与总体前后期相关系数的关系。

With the aid of Lebesgue decompositions of the n dimensional survival probability distribution functions about the age process in Poisson Process, and by the use of the maximal likelihood method and Buckely James estimate, in the paper, we give the approximate maximal likelihood estimate of the parameter λ on the population of the exponential lifetime distribution based on the Zero failure data.