Skip to main content

Table 3 Estimated error rates (ATE) and standard deviations for an increasing number of features on lymphoma data (average over 50 experiments), for each of the ranking methods.

From: Entropy-based gene ranking without selection bias for the predictive classification of microarray data

#genes E-RFE RFE SQRT-RFE CC TT
10 8.0 ± 5.3 7.5 ± 5.2 8.9 ± 5.4 11.7 ± 6.2 14.9 ± 6.9
20 5.8 ± 4.1 5.8 ± 4.5 5.4 ± 4.6 7.9 ± 5.0 11.3 ± 6.7
50 3.9 ± 4.0 4.0 ± 3.9 4.7 ± 3.9 7.3 ± 5.5 6.3 ± 4.2
100 4.1 ± 4.4 4.2 ± 4.3 4.3 ± 4.3 5.8 ± 4.8 4.7 ± 4.5
300 3.6 ± 3.8 3.7 ± 3.6 3.5 ± 3.7 3.9 ± 4.2 3.9 ± 4.4
500 3.4 ± 3.5 3.5 ± 3.6 3.5 ± 3.7 3.5 ± 3.9 3.7 ± 4.0
1000 3.7 ± 3.7 3.6 ± 3.7 3.8 ± 3.7 3.8 ± 3.8 3.8 ± 3.8
4026 All features: 3 8 ± 3 8