数据非随机缺失时单变量的分布函数估计
Estimating a Distribution Function with Missing Data
-
摘要: 本文研究数据非随机缺失下的分布函数估计问题. 在确定缺失数据是否属于某些指定区间的前提下, 对一维随机变量的分布函数作出了估计. 此时, 假定数据缺失机制形式已知, 但包含某未知多维参数. 本文证明了未知参数的估计量的相合性和渐近正态性, 也证明了分布函数的估计量的相合性和渐近正态性Abstract: In this paper, if some extra interval data are available, that is, we assume we can know for sure whether the missing data belong to some prescribed intervals or not, and the missing data mechanism is known up to a -dimension unknown parameter , then, the estimators of the underlying distribution function and the unknown parameter can be derived, and their asymptotical properties are studied