合理进行多元分析——探索性因子分析  

Reasonably carry out multivariate analysis:exploratory factor analysis

作　　者：胡纯严 胡良平 Hu Chunyan;Hu Liangping(Graduate School,Academy of Military Sciences PLA China,Beijing 100850,China;Specialty Committee of Clinical Scientific Research Statistics of World Federation of Chinese Medicine Societies,Beijing 100029,China)

机构地区：[1]军事科学院研究生院,北京100850 [2]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

出　　处：《四川精神卫生》2024年第S1期24-29,共6页Sichuan Mental Health

摘　　要：本文目的是介绍与探索性因子分析有关的基本概念、计算方法、两个实例以及使用SAS实现计算的方法。基本概念包括公因子与特殊因子、因子载荷、公因子方差和因子碎石图;计算方法涉及因子分析的数学模型、主成分法、主因子法、质心法和最大似然法;两个实例的资料分别是“31个省级政府门户网站的评估数据”和“全国各地区基本建设投资来源”;借助SAS软件,对两个实例中的数据进行了探索性因子分析,并对SAS输出结果做出了解释。The purpose of this article was to introduce the basic concepts,calculation methods,two examples related to the exploratory factor analysis,and how to implement calculations using SAS.Basic concepts included common factors and special factors,factor loadings,common factor variances and factor scree plots.The calculation methods involved the mathematical model of factor analysis,principal component method,principal factor method,centroid method and maximum likelihood method.The data in the two examples were"evaluation data of 31 provincial government portal websites"and"sources of basic construction investment in various regions across the country".With the help of SAS software,the exploratory factor analysis was conducted on the data in the two examples,and an explanation was given to the SAS output results.

关 键 词：因子模型 因子载荷 因子轴旋转 主成分法 最大似然法 

分 类 号：R195.1[医药卫生—卫生统计学]