...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Statistical and Econometric Methods >Some zero mean classification functions with unequal prior probabilities and non-normality
【24h】

Some zero mean classification functions with unequal prior probabilities and non-normality

机译：一些具有均等先验概率和非正态性的零均值分类函数

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this study, the problem of classifying a newobservation vector into one of the known groups (πi , i=1,2) distributedmultivariate normal when the mean vectors are equal and the training datacontaminated with outliers to be non-normal. Four classification rules areconsidered for equal and unequal prior probabilities and non-normality basedon: Bartlett and Please method (BPM), Bayesian Posterior Probability Approach(BPP), the Quadratic Discriminant Function (QDF) and the Absolute EuclideanDistance Classifier method (AEDC). Female liked sex twins extracted from Stocks(1933) twin data is used for analysis and performance evaluation is based onCross Validation (CV) and Balanced Error Rate (BER). While all four functionsrecorded higher error rates, BPM method was very sensitive to outliers. The QDFperformed better with the least error rate under non-normality. BPMoutperformed all the other classification rules under unequal priorprobabilities. Similar results were obtained from the simulation study.
机译：在这项研究中，当平均向量相等且训练数据被异常值污染为非正态向量时，将新观测向量分类为已知组（πi，i = 1,2）之一的问题是多元正态分布。根据以下四个规则，确定相等和不相等的先验概率和非正态性：Bartlett和Please方法（BPM），贝叶斯后验概率方法（BPP），二次判别函数（QDF）和绝对欧氏距离分类器方法（AEDC）。从Stocks（1933）双胞胎数据中提取的女性喜欢的双胞胎用于分析，并且基于交叉验证（CV）和平衡错误率（BER）进行绩效评估。尽管所有四个函数均记录了较高的错误率，但BPM方法对异常值非常敏感。在非正常情况下，QDF表现更好，错误率最小。 BPM在不等的先验概率下胜过所有其他分类规则。从模拟研究中获得了相似的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号