Micro AUROC
Rescaling one class’s column leaves every per-class AUROC untouched and moves micro AUROC by 0.017. Here is why.
-
-
Macro AUROC (Macro-Averaged AUROC)
Macro AUROC weights classes equally, but OvR still depends on the negative-class mixture. OvO, uncertainty, and thresholds need separate interpretation.
-
Multiclass AUROC
One-vs-rest or one-vs-one, macro or weighted or micro. Which combination produced the number matters more than the number.
-
Mann–Whitney U Test
AUC = U/(n1 n2) holds for the positive group’s U. Using min(U1, U2) turns 0.9600 into 0.0400.
-
DeLong’s Test
A case-resampling bootstrap gives 0.015711 where DeLong’s closed form gives 0.015541.
-
ROC-AUC
Two models with the same area can differ 2.5-fold in what they catch at a workable false positive rate. What to report beside the number.
-
Classification Metrics and Decision Thresholds
Ranking, probability, and decision are three separate things to evaluate.