1. | Calculate feature importance on the training data |
---|---|
 |    a. Gini importance |
 |    b. absolute value of regression coefficients (PLS/PCR) |
 |    c. p-values from Wilcoxon-test/t-test |
2. | Rank the features according to the importance measure, remove the p% least important |
3. | Train the classifier on the training data |
 |    A. Random forest |
 |    B. D-PLS |
 |    C. D-PCR |
 | and apply it to the test data |
4. | Repeat 1.–4. until no features are remaining |
5. | Identify the best feature subset according to the test error |