Table 3.
Results of simulation S4
| Test | p KS | R 1 | R 5 | Sensitivity | Specificity | AUC |
|---|---|---|---|---|---|---|
| NEAT | 0.399 | 1.33 | 1.14 | 69 % | 94 % | 0.920 |
| NEA | 0.001 | 0 | 0.87 | 68 % | 96 % | 0.918 |
| LP | 0 | 2.13 | 1.51 | 68 % | 92 % | 0.908 |
| LA | 0.255 | 1.60 | 1.17 | 60 % | 94 % | 0.897 |
| LA+S | 0.409 | 1.87 | 1.17 | 63 % | 94 % | 0.913 |
| NP | 0.037 | 1.24 | 1.28 | 58 % | 94 % | 0.884 |
The best results for each indicator are in bold. p KS denotes the p-value of the Kolmogorov-Smirnov test for uniform distribution, AUC is an abbreviation for “area under the ROC curve”. The distribution of p-values under H 0 is evidently not uniform for NEA and LP. NEAT shows the highest values of sensitivity and AUC, and its specificity is close to the target value (95 %)