Asymptotic Normality of Wavelet Density Estimator under Censored Dependent Observations  

作　　者：Si-li NIU 

机构地区：[1]Department of Mathematics,Tongji University

出　　处：《Acta Mathematicae Applicatae Sinica》2012年第4期781-794,共14页应用数学学报（英文版）

基　　金：Supported by the National Natural Science Foundation of China (No.10871146)

摘　　要：In this paper, we discuss the asymptotic normality of the wavelet estimator of the density function based on censored data, when the survival and the censoring times form a stationary α-mixing sequence. To simulate the distribution of estimator such that it is easy to perform statistical inference for the density function, a random weighted estimator of the density function is also constructed and investigated. Finite sample behavior of the estimator is investigated via simulations too.In this paper, we discuss the asymptotic normality of the wavelet estimator of the density function based on censored data, when the survival and the censoring times form a stationary α-mixing sequence. To simulate the distribution of estimator such that it is easy to perform statistical inference for the density function, a random weighted estimator of the density function is also constructed and investigated. Finite sample behavior of the estimator is investigated via simulations too.

关 键 词：Wavelet density estimator asymptotic normality  censored data  α-mixing  random weightedestimator 

分 类 号：O211.3[理学—概率论与数理统计]