The disagreeable behaviour of the kappa statistic

被引：53

作者：

Flight, Laura ^{[1
]}

Julious, Steven A. ^{[1
]}

机构：

[1] Univ Sheffield, Med Stat Grp, Sheffield S1 4DA, S Yorkshire, England

来源：

PHARMACEUTICAL STATISTICS | 2015年 / 14卷 / 01期

关键词：

kappa statistic; concordance; agreement; PABAK; AGREEMENT; PREVALENCE;

D O I：

10.1002/pst.1659

中图分类号：

R9 [药学];

学科分类号：

1007 ;

摘要：

It is often of interest to measure the agreement between a number of raters when an outcome is nominal or ordinal. The kappa statistic is used as a measure of agreement. The statistic is highly sensitive to the distribution of the marginal totals and can produce unreliable results. Other statistics such as the proportion of concordance, maximum attainable kappa and prevalence and bias adjusted kappa should be considered to indicate how well the kappa statistic represents agreement in the data. Each kappa should be considered and interpreted based on the context of the data being analysed. Copyright (c) 2014 JohnWiley & Sons, Ltd.

引用

页码：74 / 78

页数：5

共 10 条

[1]

Altman D. G., 1991, PRACTICAL STAT MED R, P404

[2]

Blochs DA, 1989, BIOMETRICS, V45, P269

[3] BIAS, PREVALENCE AND KAPPA [J].