Table 1

Results on simulated data for 1 feature with different level of within sample heterogeneity in the different classes.


HierNB Classifier
 StNB Classifier
Exp
 σ22
 Acc
 Brier
 Acc
 Brier
1
 15
 0.620 [0.604 0.636]
 0.449
 0.559 [0.539 0.580]
 0.490
2
 30
 0.762 [0.740 0.790]
 0.307
 0.560 [0.540 0.580]
 0.490
3
 45
 0.830 [0.813 0.849]
 0.228
 0.554 [0.537 0.570]
 0.490
4
 60
 0.878 [0.866 0.888]
 0.176
 0.556 [0.531 0.582]
 0.490
5
 75
 0.899 [0.883 0.914]
 0.147
 0.560 [0.534 0.586]
 0.490

Exp = experiment number, Acc = Accuracy, Brier = Brier Score. In brackets the 95% confidence intervals for the estimate of the accuracy.

Demichelis et al. BMC Bioinformatics 2006 7:514   doi:10.1186/1471-2105-7-514