|
| 无序样品聚类分析——基于第4组距离法和centroid法 |
| Cluster analysis of disordered samples¾Based on the fourth set of distance methods and the centroid methodHu Chunyan1, Hu Liangping1,2* |
| 投稿时间：2024-03-21 修订日期：2024-03-21 |
| DOI： |
| 中文关键词: 不对称名义变量 无序样品 Dice系数 谱系聚类分析 树形图 |
| 英文关键词:een two classes of |
| 基金项目: |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 本文目的是介绍与无序样品聚类分析有关的基本概念、计算方法、两个实例及其用SAS实现计算的方法。基本概念包括不对称名义变量、不对称比率变量、Dice系数和Kulcynski 1系数；计算方法涉及度量两个样品之间距离大小的第4组距离法(共8个)和度量两类样品之间距离大小的centroid法(即质心法)；两个实例中的资料分别是“九个离婚理由是否适用于美国各州”和“缺血性中风病患者首发证候情况”；借助SAS软件,对第1个实例中的数据进行了无序样品聚类分析,对SAS输出结果给出了解释。 |
| 英文摘要: |
| The purpose of the paper was to introduce the basic concepts, calculation methods, two examples, and the implementation of SAS calculation methods related to the cluster analysis of unordered samples. The basic concepts included asymmetric nominal variables, asymmetric ratio variables, Dice coefficient, and Kulcynski 1 coefficient; The calculation methods involved measuring the distance between two samples using the 4th set of distance methods (8 in total) and measuring the distance between two classes of samples using the centroid method; The data in the two examples were "whether the nine divorce reasons apply to each state in the United States" and "the first symptom situation of ischemic stroke patients"; Using SAS software, unordered sample clustering analysis was performed on the data in the first instance, and the SAS output results were explained. |
| 查看/发表评论 下载PDF阅读器 |
| 关闭 |