The Fleiss’ kappa statistic is a well-known index for assessing the reliability of agreement between raters. It is used both in the psychological and in the psychiatric field. Unfortunately, the kappa statistic may behave inconsistently in case of strong agreement between raters, since this index assumes lower values than it would have been expected. The aim of this paper is to propose a new method to avoid this paradox through permutation techniques. Furthermore, we study the problem of kappa confidence intervals and, in particular, we suggest to use Bootstrap confidence intervals free of paradoxes.

Falotico, R., Quatto, P. (2015). Fleiss’ Kappa statistic without paradoxes. QUALITY & QUANTITY, 49(2), 463-470 [10.1007/s11135-014-0003-1].

Fleiss’ Kappa statistic without paradoxes

FALOTICO, ROSA
;
QUATTO, PIERO
2015

Abstract

The Fleiss’ kappa statistic is a well-known index for assessing the reliability of agreement between raters. It is used both in the psychological and in the psychiatric field. Unfortunately, the kappa statistic may behave inconsistently in case of strong agreement between raters, since this index assumes lower values than it would have been expected. The aim of this paper is to propose a new method to avoid this paradox through permutation techniques. Furthermore, we study the problem of kappa confidence intervals and, in particular, we suggest to use Bootstrap confidence intervals free of paradoxes.
Campo DC Valore Lingua
dc.authority.academicField2024 Settore STAT-01/A - Statistica *
dc.authority.ancejournal QUALITY & QUANTITY -
dc.authority.people FALOTICO, ROSA en
dc.authority.people QUATTO, PIERO en
dc.collection.id.s e39773c1-7ce2-35a3-e053-3a05fe0aac26 *
dc.collection.name 01 - Articolo su rivista *
dc.contributor.appartenenza DIPARTIMENTO DI ECONOMIA, METODI QUANTITATIVI E STRATEGIE DI IMPRESA *
dc.contributor.appartenenza.mi 4406 *
dc.contributor.area AREA MIN. 13 - SCIENZE ECONOMICHE E STATISTICHE *
dc.date.accessioned 2014/05/06 14:14:54 -
dc.date.available 2014/05/06 14:14:54 -
dc.date.issued 2015 en
dc.date.submission 2019/02/18 16:43:34 *
dc.description.abstracteng The Fleiss’ kappa statistic is a well-known index for assessing the reliability of agreement between raters. It is used both in the psychological and in the psychiatric field. Unfortunately, the kappa statistic may behave inconsistently in case of strong agreement between raters, since this index assumes lower values than it would have been expected. The aim of this paper is to propose a new method to avoid this paradox through permutation techniques. Furthermore, we study the problem of kappa confidence intervals and, in particular, we suggest to use Bootstrap confidence intervals free of paradoxes. -
dc.description.allpeople Falotico, R; Quatto, P -
dc.description.allpeopleoriginal Falotico, R; Quatto, P en
dc.description.fulltext reserved en
dc.description.fulltextoriginal mixed en
dc.description.international No en
dc.description.numberofauthors 2 -
dc.identifier.citation Falotico, R., Quatto, P. (2015). Fleiss’ Kappa statistic without paradoxes. QUALITY & QUANTITY, 49(2), 463-470 [10.1007/s11135-014-0003-1]. en
dc.identifier.doi 10.1007/s11135-014-0003-1 en
dc.identifier.isi WOS:000352509200003 -
dc.identifier.scopus 2-s2.0-84957962535 -
dc.identifier.uri http://hdl.handle.net/10281/51436 -
dc.language.iso eng en
dc.publisher.name Springer Netherlands -
dc.relation.firstpage 463 en
dc.relation.issue 2 en
dc.relation.lastpage 470 en
dc.relation.numberofpages 8 en
dc.relation.volume 49 en
dc.subject.keywords Bootstrap confidence intervals; Fleiss’ kappa; Inter-rater agreement; Kappa paradoxes; Monte Carlo simulations; -
dc.subject.keywordseng Inter-rater agreement; Fleiss’ kappa; Kappa paradoxes; Monte Carlo simulations; Bootstrap confidence intervals -
dc.subject.singlekeyword Inter-rater agreement *
dc.subject.singlekeyword Fleiss’ kappa *
dc.subject.singlekeyword Kappa paradoxes *
dc.subject.singlekeyword Monte Carlo simulations *
dc.subject.singlekeyword Bootstrap confidence intervals *
dc.title Fleiss’ Kappa statistic without paradoxes en
dc.type Articolo su rivista -
dc.type.circulation Rilevanza internazionale it
dc.type.contribution Articolo in rivista - Articolo scientifico en
dc.type.driver info:eu-repo/semantics/article -
dc.type.full Pubblicazioni::01 - Articolo su rivista it
dc.type.impactfactor si it
dc.type.miur 262 en
dc.type.publicationstatus Pubblicato en
dc.type.referee Esperti anonimi en
dc.type.research Scientifica en
iris.isi.extIssued 2015 -
iris.isi.extTitle Fleiss' kappa statistic without paradoxes -
iris.mediafilter.data 2025/04/05 13:30:08 *
iris.orcid.lastModifiedDate 2023/06/02 15:38:20 *
iris.orcid.lastModifiedMillisecond 1685713100931 *
iris.scopus.extIssued 2015 -
iris.scopus.extTitle Fleiss’ kappa statistic without paradoxes -
iris.sitodocente.maxattempts 1 -
iris.unpaywall.doi 10.1007/s11135-014-0003-1 *
iris.unpaywall.isoa false *
iris.unpaywall.journalisindoaj false *
iris.unpaywall.metadataCallLastModified 03/04/2025 04:13:42 -
iris.unpaywall.metadataCallLastModifiedMillisecond 1743646422867 -
iris.unpaywall.oastatus closed *
isi.authority.ancejournal QUALITY & QUANTITY###0033-5177 *
isi.category XY *
isi.category WU *
isi.contributor.affiliation University of Milano-Bicocca -
isi.contributor.affiliation University of Milano-Bicocca -
isi.contributor.country Italy -
isi.contributor.country Italy -
isi.contributor.name Rosa -
isi.contributor.name Piero -
isi.contributor.researcherId EWO-9499-2022 -
isi.contributor.researcherId GVS-8344-2022 -
isi.contributor.subaffiliation Dept Econ Management & Stat -
isi.contributor.subaffiliation Dept Econ Management & Stat -
isi.contributor.surname Falotico -
isi.contributor.surname Quatto -
isi.date.issued 2015 *
isi.description.allpeopleoriginal Falotico, R; Quatto, P; *
isi.document.sourcetype WOS.SCI *
isi.document.type Article *
isi.document.typenorm Articolo in rivista - Articolo scientifico *
isi.document.types Article *
isi.identifier.doi 10.1007/s11135-014-0003-1 *
isi.identifier.eissn 1573-7845 *
isi.identifier.isi WOS:000352509200003 *
isi.journal.journaltitle QUALITY & QUANTITY *
isi.journal.journaltitleabbrev QUAL QUANT *
isi.language.original English *
isi.publisher.place VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS *
isi.relation.firstpage 463 *
isi.relation.issue 2 *
isi.relation.lastpage 470 *
isi.relation.volume 49 *
isi.title Fleiss' kappa statistic without paradoxes *
scopus.authority.ancejournal QUALITY & QUANTITY###0033-5177 *
scopus.category 2613 *
scopus.category 3300 *
scopus.contributor.affiliation University of Milan-Bicocca -
scopus.contributor.affiliation University of Milan-Bicocca -
scopus.contributor.afid 60012306 -
scopus.contributor.afid 60012306 -
scopus.contributor.auid 56029633300 -
scopus.contributor.auid 6503868442 -
scopus.contributor.country Italy -
scopus.contributor.country Italy -
scopus.contributor.dptid 113551627 -
scopus.contributor.dptid 113551627 -
scopus.contributor.name Rosa -
scopus.contributor.name Piero -
scopus.contributor.subaffiliation Department of Economics;Management and Statistics; -
scopus.contributor.subaffiliation Department of Economics;Management and Statistics; -
scopus.contributor.surname Falotico -
scopus.contributor.surname Quatto -
scopus.date.issued 2015 *
scopus.description.abstracteng The Fleiss’ kappa statistic is a well-known index for assessing the reliability of agreement between raters. It is used both in the psychological and in the psychiatric field. Unfortunately, the kappa statistic may behave inconsistently in case of strong agreement between raters, since this index assumes lower values than it would have been expected. The aim of this paper is to propose a new method to avoid this paradox through permutation techniques. Furthermore, we study the problem of kappa confidence intervals and, in particular, we suggest to use Bootstrap confidence intervals free of paradoxes. *
scopus.description.allpeopleoriginal Falotico R.; Quatto P. *
scopus.differences scopus.description.allpeopleoriginal -
scopus.document.type ar *
scopus.document.types ar *
scopus.identifier.doi 10.1007/s11135-014-0003-1 *
scopus.identifier.eissn 1573-7845 *
scopus.identifier.pui 608240975 *
scopus.identifier.scopus 2-s2.0-84957962535 *
scopus.journal.sourceid 19372 *
scopus.language.iso eng *
scopus.publisher.name Springer Netherlands *
scopus.relation.firstpage 463 *
scopus.relation.issue 2 *
scopus.relation.lastpage 470 *
scopus.relation.volume 49 *
scopus.subject.keywords Bootstrap confidence intervals; Fleiss’ kappa; Inter-rater agreement; Kappa paradoxes; Monte Carlo simulations; *
scopus.title Fleiss’ kappa statistic without paradoxes *
scopus.titleeng Fleiss’ kappa statistic without paradoxes *
Appare nelle tipologie: 01 - Articolo su rivista
File in questo prodotto:
File Dimensione Formato  
FleissKappaStatisticWithoutPar.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 133.97 kB
Formato Adobe PDF
133.97 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/51436
Citazioni
  • Scopus 156
  • ???jsp.display-item.citation.isi??? 118
Social impact