Figure 7.
Cross-validation error for SVM, RLDA and LPM against the number of best-ranked features. A 10-fold cross-validation was repeated 5 times and standard errors are plotted. The SVM and LPM hyperparameters were selected by an outer cross validation. The number of 6 best-ranked features was determined for building the final classifier, as the estimated error of the RLDA starts to increase significantly for higher numbers of features.