首页 | 本学科首页   官方微博 | 高级检索  
     

利用Origin对数据异常值的剔除方法进行比较
引用本文:张璇,程敏熙,肖凤平. 利用Origin对数据异常值的剔除方法进行比较[J]. 实验科学与技术, 2012, 10(1): 74-76,118
作者姓名:张璇  程敏熙  肖凤平
作者单位:华南师范大学物理与电信工程学院,广州,510006
摘    要:
介绍了采用拉依达准则、肖维勒准则、格拉布斯准则以及狄拉克准则4种剔除异常数据的方法,简述了各准则的数理统计原理、处理步骤,并借助Origin软件对处理某次盐液体电导率实验的数据,对比了各准则剔除异常值后的处理结果.指出在大样本情况下较适合用拉依达准则,而肖维勒准则和狄拉克准则适用于样本容量较小的情况,格拉布斯准则则适用性和剔除结果较为普遍。

关 键 词:Origin软件  异常值  拉依达准则  肖维勒准则  格拉布斯准则  狄克逊准则

Origin Used in Comparison the Methods of Eliminating the Excrescent Data
ZHANG Xuan,CHENG Min-xi,XIAO Feng-ping. Origin Used in Comparison the Methods of Eliminating the Excrescent Data[J]. Experiment Science & Technology, 2012, 10(1): 74-76,118
Authors:ZHANG Xuan  CHENG Min-xi  XIAO Feng-ping
Affiliation:(School of Physics and Telecommunication Engineering,South China Normal University,Guangzhou 510006,China)
Abstract:
Four criterions are introduced in this paper to eliminate and distinguish the abnormal values,they are PauT a,Chauv-enet,Grubbs,and Dixon.Their mathematic statistics principles and concordances are also resumed in this paper.Origin software are used to deal with experimental data of conductivity of solution and to compare the processing results.It pointed out that PauT a and Chauv-enet are suitable for large sample and Grubbs,Dixon is suitable for small sample.The Grubbs criterion is in common use.
Keywords:Origin software  abnormal value  PauT a  Chauv-enet  Grubbs  Dixon
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