Saved in:
Bibliographic Details
Main Author: Manuel Ato
Format: Artículo científico
Language:en
Published: Universitat de València 2012
Subjects:
Online Access:https://www.redalyc.org/articulo.oa?id=16923102012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866583505953095680
author Manuel Ato
author_facet Manuel Ato
contents A simulation study of rater agreement measures with 2x2 contingency tables Manuel Ato Juan José López Ana Benavente Psicología A comparison between six rater agreement measures obtained using three different approaches was achieved by means of a simulation study. Rater coefficients suggested by Bennet´s o (1954), Scott´s T (1955), Cohen´s K (1960) and Gwet´s Y (2008) were selected to represent the classical, descriptive approach, a agreement parameter from Aickin (1990) to represent loglinear and mixture model approaches and A measure from Martín and Femia (2004) to represent multiple-choice test. Main results confirm that T and K descriptive measures present high levels of mean bias in presence of extreme values of prevalence and rater bias but small to null levels with moderate values. The best behavior was observed with Bennet and Martín and Femia agreement measures for all levels of prevalence. 2012 artículo científico 0211-2159 https://www.redalyc.org/articulo.oa?id=16923102012 en http://www.redalyc.org/revista.oa?id=169 Psicológica application/pdf Universitat de València Psicológica (España) Num.2 Vol.33
format Artículo científico
id redalyc_16923102012
language en
publishDate 2012
publisher Universitat de València
spellingShingle A simulation study of rater agreement measures with 2x2 contingency tables
Manuel Ato
Psicología
A simulation study of rater agreement measures with 2x2 contingency tables Manuel Ato Juan José López Ana Benavente Psicología A comparison between six rater agreement measures obtained using three different approaches was achieved by means of a simulation study. Rater coefficients suggested by Bennet´s o (1954), Scott´s T (1955), Cohen´s K (1960) and Gwet´s Y (2008) were selected to represent the classical, descriptive approach, a agreement parameter from Aickin (1990) to represent loglinear and mixture model approaches and A measure from Martín and Femia (2004) to represent multiple-choice test. Main results confirm that T and K descriptive measures present high levels of mean bias in presence of extreme values of prevalence and rater bias but small to null levels with moderate values. The best behavior was observed with Bennet and Martín and Femia agreement measures for all levels of prevalence. 2012 artículo científico 0211-2159 https://www.redalyc.org/articulo.oa?id=16923102012 en http://www.redalyc.org/revista.oa?id=169 Psicológica application/pdf Universitat de València Psicológica (España) Num.2 Vol.33
title A simulation study of rater agreement measures with 2x2 contingency tables
topic Psicología
url https://www.redalyc.org/articulo.oa?id=16923102012