基于长记忆函数型数据条件中位数的相合估计  

Consistency of the conditional median for functional data under long-memory condition

作　　者：赵云云[1] 凌能祥[1] 

机构地区：[1]合肥工业大学数学学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2010年第6期947-950,共4页Journal of Hefei University of Technology：Natural Science

基　　金：合肥工业大学精品课程资助项目(YJC2008Y07)

摘　　要：文章研究了当解释变量取值在某个抽象的函数空间上时条件中位数的非参数估计,给出了基于长记忆函数型数据条件中位数的核估计,并且在一定的条件下建立了估计量的相合性,给出了基于长记忆函数型数据条件分位数的核估计量在相应条件下的相合性。This paper studies the nonparametric estimation of conditional median when the explanatory variable takes values in certain abstract functional space. The kernel estimation is conducted by the functional data under long-memory condition and the consistency of the estimator is constructed under certain condition. Then the convergence of the kernel estimation of conditional quantile based on func- tional data under long-memorv condition is presented.

关 键 词：函数型数据 条件中位数 核估计 依概率收敛 

分 类 号：O212.7[理学—概率论与数理统计]