首页 | 本学科首页   官方微博 | 高级检索  
     

回归模型中变点识别的一种稳健方法
引用本文:王惠惠,魏立力. 回归模型中变点识别的一种稳健方法[J]. 计算机仿真, 2008, 25(2): 93-95,144
作者姓名:王惠惠  魏立力
作者单位:宁夏大学数学与计算机学院,宁夏,银川,750021;宁夏大学数学与计算机学院,宁夏,银川,750021
基金项目:教育部科学技术研究重点项目 , 宁夏自然科学基金
摘    要:变点识别是数据分析中一个非常重要的研究内容.文中针对目前变点识别研究中忽略了方法的稳健性,未能充分考虑异常值的影响的不足,提出利用一种高度稳健的回归类混合分解算法来识别变点.该方法从混合回归模型的角度,将含有变点的回归模型看作回归类的混合,通过逐步挖掘数据集中的回归类,并对排序后的回归类进行分析,进而确定变点的位置及个数.数值模拟表明,在识别变点的过程中无须预先指定变点的数目,并且具有高度的稳健性和有效性.

关 键 词:回归变点  稳健  回归类
文章编号:1006-9348(2008)02-0093-03
收稿时间:2007-01-02
修稿时间:2007-02-01

A Robust Method for Change-Points Detection in Regression Model
WANG Hui-hui,WEI Li-li. A Robust Method for Change-Points Detection in Regression Model[J]. Computer Simulation, 2008, 25(2): 93-95,144
Authors:WANG Hui-hui  WEI Li-li
Abstract:Change-points detection is one of the most important problems in data analysis. Traditional investi-gations on the detection of change-points considering little infection of noise always ignore the robust of the methods. In this paper, a highly robust regression - class mixture decomposition method is proposed for finding change - point in a large data set. In the method, based on the mixture of regression model, the regression model with change - point is regards as the mixture of many regression - classes. Different regression classes are mined sequentially in the data set, and then the number and the position of change - points can be determined by analysing the regression classes having been arranged. The experiments demonstrate that the number of change points which can be gotten automatically, will not be prespecified, and this method is very robust and effective in change point detection.
Keywords:Regression change - points   Robust   Regression - class
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号