Logo do repositório
 
Publicação

Accuracy measures for binary classification based on a quantitative variable

2019-04Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorSantos, Rui
dc.contributor.authorFelgueiras, Miguel
dc.contributor.authorMartins, João Paulo
dc.contributor.authorFerreira, Liliana
dc.date.accessioned2026-03-17T17:42:58Z
dc.date.available2026-03-17T17:42:58Z
dc.date.issued2019-04
dc.description.abstractThe identification of the right methodology to perform binary classification based on an observed quantitative variable is usually a complex choice. Thus, the use of appropriate accuracy measures is crucial. In fact, the ROC curve reveals a lot of information about the accuracy of the applied methodology for all the possible values of the cut-point. In particular, the integral and partial areas under the ROC curve are widely used. The φ index, in which sensitivity equals specificity, may also be applied. Nevertheless, the accuracy at one specific cut-point may be sufficient to assess the accuracy in some applications. Therefore, different ways to define the optimal cut-point may be applied, such as the maximization of the Youden index, the maximization of the concordance probability or the minimization of the distance to the point with absence of misclassification. To compare the adequacy of these measures, a simulation study was performed under different scenarios. The results highlight the advantages and disadvantages of each procedure and advise the use of the φ index.eng
dc.description.sponsorshipThis work has been funded by FCT - Fundacao Nacional para a Ciencia e Tecnologia, Portugal, through the projects UID/MAT/00006/2013, UID/MAT/ 04561/2013, UID/MAT/00006/2019 and UID/MAT/04561/2019.
dc.identifier.citationSantos , R., Felgueiras , M., Martins , J. P., & Liliana Ferreira , L. F. . (2019). Accuracy Measures for Binary Classification Based on a Quantitative Variable. REVSTAT-Statistical Journal, 17(2), 223-244. https://doi.org/10.57805/revstat.v17i2.266
dc.identifier.doi10.57805/revstat.v17i2.266
dc.identifier.issn1645-6726
dc.identifier.urihttp://hdl.handle.net/10400.8/15902
dc.language.isoeng
dc.peerreviewedyes
dc.publisherInstituto Nacional de Estatística
dc.relation.hasversionhttps://revstat.ine.pt/index.php/REVSTAT/article/view/266
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectBinary classification
dc.subjectcut-point
dc.subjectROC curve
dc.subjectsensitivity
dc.subjectspecificity
dc.subjectsimulation
dc.titleAccuracy measures for binary classification based on a quantitative variableeng
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage244
oaire.citation.startPage223
oaire.citation.titleREVSTAT
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameSantos
person.familyNameFelgueiras
person.familyNameOliveira Martins
person.familyNameFerreira
person.givenNameRui
person.givenNameMiguel
person.givenNameJoão Paulo
person.givenNameLiliana
person.identifier1051057
person.identifier.ciencia-id7610-8B27-8044
person.identifier.ciencia-id0F1B-DE05-36E5
person.identifier.orcid0000-0002-7371-363X
person.identifier.orcid0000-0001-5450-7374
person.identifier.orcid0000-0002-0474-1397
person.identifier.orcid0000-0002-3362-996X
person.identifier.ridC-1873-2015
person.identifier.ridM-8134-2019
person.identifier.scopus-author-id56979441000
person.identifier.scopus-author-id50861001200
relation.isAuthorOfPublicationfba82887-7d94-41f6-a4aa-06b7de054567
relation.isAuthorOfPublicationb7404fe1-3566-46d5-9d02-341bec92615b
relation.isAuthorOfPublicationb3dba60a-968a-47e9-87e2-b238acdbc75d
relation.isAuthorOfPublication93730273-e62f-4b02-92dc-374e85a61aa3
relation.isAuthorOfPublication.latestForDiscovery93730273-e62f-4b02-92dc-374e85a61aa3

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
219.pdf
Tamanho:
953.57 KB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.32 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESTG - Artigos em revistas nacionais