Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Sample size and statistical power considerations in high-dimensionality data settings: a comparative study of classification algorithms

Figure 4

Statistical power of classifiers KNN, PAM, RF and SVM, comparing settings with and without noise. Each dataset included n = 150 subjects per class, where features were distributed according to a Gaussian distribution within each class. The setting "With Noise" corresponded to the inclusion of 1000 features per subject, where only 10 were biomarkers. The setting "Without Noise" corresponded to the inclusion of only 10 biomarkers per subject. Results are based on 100 simulated datasets.

Back to article page