Using p-values for the comparison of classifiers: pitfalls and alternatives

Daniel Berrar

2022Data Mining and Knowledge Discovery13 citationsDOI

Topics & Concepts

Null hypothesisBenchmark (surveying)Wilcoxon signed-rank testStatistical hypothesis testingNull (SQL)Value (mathematics)Artificial intelligenceRank (graph theory)Machine learningStatisticsAlternative hypothesisp-valueComputer scienceMathematicsStatistical significanceEconometricsData miningMann–Whitney U testCombinatoricsGeodesyGeographyStatistical Methods in Clinical TrialsAdvanced Statistical Methods and ModelsStatistical Methods and Inference