Comparison of average classification accuracy of classifiers when feature distributions within class are Gaussian. Each dataset included 1000 features per subject, where features were distributed according to a Gaussian distribution within each class. Results shown in Panels (a) - (c) were based on k= 1% and n= 100, 150 or 200. Results shown in Panels (d) - (f) were based on n= 150 and k= 0.5%, 1% or 5%. Results are based on 100 simulated datasets. Average classification accuracy estimates were derived based on a 4-fold cross validation procedure. See Additional File 1: Supplemental Figure S2 (a) for similar results when n= 50 and k= 1%.