Figure 4
From: To aggregate or not to aggregate high-dimensional classifiers
Boxplot of prediction errors for two real data sets. Misclassification rates are obtained from 1000 times repeating 10 fold double cross-validations. The ratios of features to samples in test sets are 34/7129 (Leukemia) and 76/412 (Grape). The model of grape data is more stable since the ratio of feature to sample is lower.