摘要
一、引言及若干引理设(X_1,Y_1),…,(X_n,Y_n)为(X,Y)的前 n 个样本,(X,Y)为 R^d×R 上的随机向量,μ为 X 的概率分布,回归函数 m(x)=E(Y|X=x)
Based on independent or (?)-mixing,α-mixing samples,the strong,weak and complete con-sistency,the integrated mean consistency for the kernel regression estimate and the improved ker-nel estimate are obtained.The class of applicable kernels includes those having unboundedsupport,and even not integrable,which extends and improves the results that are establishedby Cheng Ping,Watson,Nadarage and Devroye.
出处
《系统科学与数学》
CSCD
北大核心
1993年第2期141-151,共11页
Journal of Systems Science and Mathematical Sciences
基金
国家自然科学基金
