Skip to main content
. Author manuscript; available in PMC: 2019 Jan 1.
Published in final edited form as: Knowl Inf Syst. 2017 Nov 17;54(1):151–170. doi: 10.1007/s10115-017-1133-2

Table 6.

Average rank of the calibration methods on the benchmark datasets using NB as the base classifier. Marker */⊛ indicates whether ENIR is statistically superior/inferior to the compared method (using an improved Friedman test followed by Holm’s step-down procedure at a 0.05 significance level).

IsoRegC BBQ ENIR
AUC 2.150 1.925 1.925
ACC 1.963 2.375* 1.663
RMSE 2.200* 2.375* 1.425
ECE 2.475* 2.075* 1.450
MCE 2.563* 1.850 1.588