Two apparent paradoxes have been identified for the kappa (kappa) statistic : (1) high levels of observer agreement with low K values ; (2) lack of predictability of changes in K with changing marginals.
The first paradox is a function of prevalence of the trait in the sample, while the second is related to symmetry of observations in the disagreement categories.
While examining the behavior of K as a function of the distribution of responses in a contingency table, it was discovered that for any measured level of observer agreement (Po) there are three characteristic values of kappa : kappamax, kappamin, and kappanor, each of which is a function only of Po.
The characteristic values allow an observed kappa (kappao) to be placed into perspective.
By observing symmetry in agreement and disagreement categories, the behavior of K is readily understood and predictable.
We define symmetry expressions for agreement (SA) and disagreement (SD) in order to represent and quantify these effects.
K alone has little interpretive value and we recommend that studies reporting kappa also report Po, SD, and P+ (agreement on the presence of the trait).
Mots-clés Pascal : Analyse statistique, Indice kappa, Interprétation, Méthode calcul, Epidémiologie, Méthodologie
Mots-clés Pascal anglais : Statistical analysis, Kappa number, Interpretation, Computing method, Epidemiology, Methodology
Notice produite par :
Inist-CNRS - Institut de l'Information Scientifique et Technique
Cote : 96-0420253
Code Inist : 002B30A01A1. Création : 10/04/1997.