Figure 6
From: Multiclass classification of microarray data with repeated measurements: application to cancer
Comparison of feature stability of EWUSC, USC and SC on the breast cancer data. The average Jaccard index is plotted against the number of relevant genes over five random runs of 10-fold cross-validation using the EWUSC algorithm at ρ0 = 0.7, the USC algorithm at ρ0 = 0.6 and the SC algorithm (USC at ρ0 = 1). The EWUSC algorithm produces relatively more stable features when the number of relevant genes is small.