基于假设函数空间上样本误差的估计

广东工业大学学报 ›› 2006, Vol. 23 ›› Issue (4): 98-100.

基于假设函数空间上样本误差的估计

广东工业大学应用数学学院；广东工业大学应用数学学院广东广州510090；广东广州510090；

出版日期:2006-11-10 发布日期:2006-11-10

Estimation of Sample Error Based on Hypothesis Space

(Faculty of Applied Mathematics,Guangdong University of Technology,Guangzhou 510090,China)

Online:2006-11-10 Published:2006-11-10

摘要/Abstract

摘要： 在传统回归分析中,基于已知样本寻找最优函数一般在某个已知函数空间,如多项式空间,对数以及指数空间等,对于样本个数一定的情况下,样本误差会随着函数空间的增大而增大.在本文中,作者用概率测度、覆盖原理在有界函数空间中给出一个样本误差估计的方法.

关键词: 样本误差:覆盖原理；有界函数空间；概率测度；

Abstract: In traditional regress analysis,a good regression function is found in some function space based on known samples,such as polynomial function space,logarithm space and exponent space,When the sample number is certain the sample error will be big with the widening of function apace.In this paper,a method of sample error estimation is presented by probability measure and covering theory in a bouded function space.

Key words: sample error； covering theory； bounded function space； probability measure；

王兵；曾文曲；陈鹤峰； . 基于假设函数空间上样本误差的估计[J]. 广东工业大学学报, 2006, 23(4): 98-100.

WANG Bing,ZENG Wen-qu,CHEN He-feng. Estimation of Sample Error Based on Hypothesis Space[J]. Journal of Guangdong University of Technology, 2006, 23(4): 98-100.

参考文献

[1] 汪荣鑫编著.数理统计[M]. 西安交通大学出版社, 1986

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed