|
| Liu Huigang1,Hu Chunyan2, Hu Liangping2,3*(1. School of Basic Medical Sciences, Capital Medical University, Beijing 100069,China; |
DOI： |
| English keywords:Data standardization Variable selection Wilks' λ statistic Stepwise discrimination Classification decision |
| Fund projects: |
|
| Summary clicks: |
| Full text downloads: |
| English abstract: |
| 【】The purpose of this article was to introduce the basic concepts, computational methods, two examples, and the implementation using SAS software for stepwise discriminant analysis. Basic concepts included "stepwise discriminant analysis," "data standardization," "variable selection," "Wilks" λ statistic," and "hypothesis testing." The computational methods involved "data normalization," "building an initial model," "selecting variables to enter the model," "hypothesis testing," "choosing variables to remove from the model," "constructing discriminant functions," and "classification decision-making." The data in the two examples were "measurement results of seven types of fish on six quantitative indicators" and "measurement results of three types of iris plants on four quantitative indicators." With the help of SAS software, stepwise discriminant analysis was performed on the data from both examples, and finally, the overall misclassification rates corresponding to each example were provided. |
|
View/Add Comment Download reader |
| Close |
|
|
|