raters: A Modification of Fleiss' Kappa in Case of Nominal and Ordinal Variables

The kappa statistic implemented by Fleiss is a very popular index for assessing the reliability of agreement among multiple observers. It is used both in the psychological and in the psychiatric field. Other fields of application are typically medicine, biology and engineering. 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. We propose a modification kappa implemented by Fleiss in case of nominal and ordinal variables. Monte Carlo simulations are used both to testing statistical hypotheses and to calculating percentile bootstrap confidence intervals based on proposed statistic in case of nominal and ordinal data.

Version: 2.0.1
Published: 2014-12-29
Author: Daniele Giardiello [cre], Piero Quatto [aut], Enrico Ripamonti [aut], Stefano Vigliani [ctb]
Maintainer: Daniele Giardiello <daniele.giardiello1 at gmail.com>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: raters results


Reference manual: raters.pdf
Package source: raters_2.0.1.tar.gz
Windows binaries: r-devel: raters_2.0.1.zip, r-release: raters_2.0.1.zip, r-oldrel: raters_2.0.1.zip
OS X El Capitan binaries: r-release: raters_2.0.1.tgz
OS X Mavericks binaries: r-oldrel: raters_2.0.1.tgz
Old sources: raters archive


Please use the canonical form https://CRAN.R-project.org/package=raters to link to this page.