Skip to main content

Table 2 Evaluation of two classifiers A and B on separate datasets

From: The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation

Classifier dataset TP FN TN FP ϕ TPR TNR BM MCC   
(a) Relative CM
A 1 0.35 0.15 0.35 0.15 0.5 0.7 0.7 0.4 0.4   
B 2 0.04 0.01 0.76 0.19 0.05 0.8 0.8 0.6 0.3   
Classifier dataset TP FN TN FP ϕ TPR TNR BM MCC n+ n–
(b) Exemplary CM for a sample size of 200
A 1 70 30 70 30 0.5 0.7 0.7 0.4 0.4 100 100
B 2 8 2 152 38 0.05 0.8 0.8 0.6 0.3 10 190
  1. In the literature, different publications compare classifiers for the same task on separate datasets. This poses a problem for the comparability of metrics which are dependent on prevalence
\