胡纯严,胡良平.合理进行多元分析——主成分分析[J].四川精神卫生杂志,2023,36(S1):48-54.Hu Chunyan,Hu Liangping,Reasonably carry out multivariate analysis: principal component analysis[J].SICHUAN MENTAL HEALTH,2023,36(S1):48-54
合理进行多元分析——主成分分析
Reasonably carry out multivariate analysis: principal component analysis
投稿时间:2023-06-05  
DOI:10.11886/scjsws20230605001
中文关键词:  特征值  特征向量  主成分分析  样品聚类  样品排序
英文关键词:Eigenvalue  Eigenvector  Principal component analysis  Sample clustering  Sample sorting
基金项目:
作者单位邮编
胡纯严 军事科学院研究生院北京 100850 100850
胡良平* 军事科学院研究生院北京 100850
世界中医药学会联合会临床科研统计学专业委员会北京 100029 
100029
摘要点击次数:
全文下载次数:
中文摘要:
      本文目的是介绍与主成分分析有关的基本概念、计算方法、两个实例以及SAS实现。基本概念包括相关矩阵、特征值与特征向量、主成分变量、主成分表达式和主成分的性质;计算方法涉及特征值与特征向量的求法、主成分分析的计算原理以及系数估计和个数的确定;两个实例中的资料分别为“20例肝病患者的4项肝功能指标的测定结果”和“23种肿瘤类期刊的文献计量学指标的调查结果”;借助SAS对两个实例中的定量资料进行了主成分分析,并基于主成分的计算结果分别实现了样品聚类和样品排序,并对输出结果作出了解释。
英文摘要:
      The purpose of this article was to introduce the basic concepts, calculation methods, two examples and SAS implementation related to the principal component analysis. Basic concepts included correlation matrix, eigenvalues and eigenvectors, principal component variables, principal component expressions and principal component properties. The calculation method involved the calculation of eigenvalues and eigenvectors, the calculation principle and the coefficient estimation and the number determination of the principal component. The data in the two examples were measurement results of 4 liver function indicators in 20 patients with liver disease and survey results of literature metrology indicators in 23 tumor journals.With the help of SAS software, the principal component analysis was carried out on the quantitative data in the two cases, and based on the calculation results of the principal components, the sample clustering and sample sorting were respectively realized, and a reasonable explanation was given for the output results.
查看全文  查看/发表评论  下载PDF阅读器
关闭