. 2016 Dec 20;2016:6794916. doi: 10.1155/2016/6794916

Table 2.

Average R² estimates of learning techniques with 100 repetitions.

Dataset	SVR (lin)	SVR (pol)	SVR bagging	RT	RT bagging	GBM
GSE1938	0.962^∗∗	0.874^∗∗	0.941^∗∗↓	0.838^∗∗	0.724^∗∗↓	0.943^∗∗↑
GSE12817	0.978^∗∗	0.925^∗∗	0.963^∗∗↓	0.792^∗∗	0.847^∗∗↑	0.945^∗∗↑
GSE3078	0.639^∗	0.583^∗	0.538^∗↓	0.759^∗∗	0.739^∗∗↓	0.760^∗∗↑
GSE10748	0.367	0.289	0.303↓	0.254	0.290↑	0.263↑
GSE15457	0.879^∗∗	0.407^∗	0.769^∗∗↓	0.720^∗∗	0.231↓	0.884^∗∗↑
GSE8982	0.740^∗∗	0.686^∗∗	0.574^∗∗↓	0.593^∗∗	0.616^∗∗↑	0.720^∗∗↑
GSE14954	0.804^∗∗	0.653^∗∗	0.710^∗∗↓	0.426^∗	0.584^∗∗↑	0.781^∗∗↑
GSE9751	0.552^∗∗	0.363^∗	0.457^∗↓	0.135	0.275↑	0.275↑
GSE7955	0.549^∗∗	0.466^∗∗	0.443^∗↓	0.198	0.300^∗↑	0.325^∗↑
GSE2409	0.814^∗∗	0.263^∗	0.714^∗∗↓	0.440^∗∗	0.538^∗∗↑	0.644^∗∗↑
GSE9539	0.867^∗∗	0.700^∗∗	0.823^∗∗↓	0.552^∗∗	0.664^∗∗↑	0.833^∗∗↑

Bold indicates the best performance; ↑: increase in R²; ↓: decrease in R² compared to single performance. ∗∗ and ∗: significant at 0.001 and 0.05 level, respectively. SVR (lin), SVR (pol), and RT are single performances, while the others are ensemble performances of the methods.