Table 6.
Running times.
| Variable selection methods | ||
| Method | Running time per learningset | |
| Multiclass F-Test | 3.1 s | |
| Krusal-Wallis test | 3.5 s | |
| Limma* | 0.16s | |
| Random Forest†,* | 4.1 s | |
| Classification methods | ||
| Method | # variables | Running time per 50 learningsets |
| DLDA | all (2308) | 2.7 s |
| LDA | 10 | 1.4 s |
| QDA | 2 | 1.0 s |
| Partial Least Squares | all (2308) | 4.2 s |
| Shrunken Centroids | all (2308) | 2.8 s |
| SVM* | all (2308) | 88s |
Running times of the different variable selection and classification methods used in the real life example. †: 500 bootstrap trees per run.