A Comparison of MCC and CEN Error Measures in Multi-Class Prediction

We show that the Confusion Entropy, a measure of performance in multiclass problems has a strong (monotone) relation with the multiclass generalization of a classical metric, the Matthews Correlation Coefficient. Analytical results are provided for the limit cases of general no-information (n-face d...

Descripción completa

Detalles Bibliográficos
Autores principales: Jurman, Giuseppe, Riccadonna, Samantha, Furlanello, Cesare
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2012
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3414515/
https://www.ncbi.nlm.nih.gov/pubmed/22905111
http://dx.doi.org/10.1371/journal.pone.0041882
_version_ 1782240223520882688
author Jurman, Giuseppe
Riccadonna, Samantha
Furlanello, Cesare
author_facet Jurman, Giuseppe
Riccadonna, Samantha
Furlanello, Cesare
author_sort Jurman, Giuseppe
collection PubMed
description We show that the Confusion Entropy, a measure of performance in multiclass problems has a strong (monotone) relation with the multiclass generalization of a classical metric, the Matthews Correlation Coefficient. Analytical results are provided for the limit cases of general no-information (n-face dice rolling) of the binary classification. Computational evidence supports the claim in the general case.
format Online
Article
Text
id pubmed-3414515
institution National Center for Biotechnology Information
language English
publishDate 2012
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-34145152012-08-19 A Comparison of MCC and CEN Error Measures in Multi-Class Prediction Jurman, Giuseppe Riccadonna, Samantha Furlanello, Cesare PLoS One Research Article We show that the Confusion Entropy, a measure of performance in multiclass problems has a strong (monotone) relation with the multiclass generalization of a classical metric, the Matthews Correlation Coefficient. Analytical results are provided for the limit cases of general no-information (n-face dice rolling) of the binary classification. Computational evidence supports the claim in the general case. Public Library of Science 2012-08-08 /pmc/articles/PMC3414515/ /pubmed/22905111 http://dx.doi.org/10.1371/journal.pone.0041882 Text en © 2012 Jurman et al http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
spellingShingle Research Article
Jurman, Giuseppe
Riccadonna, Samantha
Furlanello, Cesare
A Comparison of MCC and CEN Error Measures in Multi-Class Prediction
title A Comparison of MCC and CEN Error Measures in Multi-Class Prediction
title_full A Comparison of MCC and CEN Error Measures in Multi-Class Prediction
title_fullStr A Comparison of MCC and CEN Error Measures in Multi-Class Prediction
title_full_unstemmed A Comparison of MCC and CEN Error Measures in Multi-Class Prediction
title_short A Comparison of MCC and CEN Error Measures in Multi-Class Prediction
title_sort comparison of mcc and cen error measures in multi-class prediction
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3414515/
https://www.ncbi.nlm.nih.gov/pubmed/22905111
http://dx.doi.org/10.1371/journal.pone.0041882
work_keys_str_mv AT jurmangiuseppe acomparisonofmccandcenerrormeasuresinmulticlassprediction
AT riccadonnasamantha acomparisonofmccandcenerrormeasuresinmulticlassprediction
AT furlanellocesare acomparisonofmccandcenerrormeasuresinmulticlassprediction
AT jurmangiuseppe comparisonofmccandcenerrormeasuresinmulticlassprediction
AT riccadonnasamantha comparisonofmccandcenerrormeasuresinmulticlassprediction
AT furlanellocesare comparisonofmccandcenerrormeasuresinmulticlassprediction

Ejemplares similares