四川精神卫生2024，Vol.37Issue(z1)：19-23,5.DOI:10.11886/scjsws20230830004
合理进行多元分析——定性资料的判别分析
Reasonably carry out multivariate analysis:qualitative data discrimination analysis
胡纯严 1胡良平2
作者信息
- 1. 军事科学院研究生院,北京 100850
- 2. 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
- 折叠
摘要
Abstract
The purpose of the paper was to introduce the basic concepts,calculation methods,two examples and SAS implementation related to the qualitative data discrimination analysis.Basic concepts included qualitative and categorical variables,discriminant analysis,maximum likelihood method,prior probability and prior distribution,posterior probability and posterior distribution.The calculation methods involved the maximum likelihood discriminant method and Bayes formula discriminant approach.The data in the two examples were"the frequency of various types of appendicitis in each detail"and"the symptoms and signs of a patient".With the help of SAS software,the discriminant analysis was carried out on the data in the two examples,and an explanation was made for the output results of SAS.关键词
定性资料/判别分析/最大似然法/先验概率/贝叶斯公式Key words
Qualitative data/Discriminant analysis/Maximum likelihood method/Prior probability/Bayes formula分类
预防医学引用本文复制引用
胡纯严,胡良平..合理进行多元分析——定性资料的判别分析[J].四川精神卫生,2024,37(z1):19-23,5.
