Figure 1.

Evaluation schemes. The top panel illustrates the splitting into learning and test data sets. The whole sample S is split into a learning set ℒ and a test set $\mathcal{T}$. The classifier f(·) is constructed using the learning set ℒ and subsequently applied to the test set $\mathcal{T}$. The bottom panel displays schematically k-fold cross-validation (left), Monte-Carlo cross-validation with n = 5 and ntrain = 3 (middle), and bootstrap sampling (with replacement) with n = 5 and ntrain = 3 (right).