HOW RELIABLE ARE CHANCE-CORRECTED MEASURES OF AGREEMENT

被引：55

作者：

GUGGENMOOSHOLZMANN, I

机构：

[1] Department of Biostatistics and Medical Informatics, Free University of Berlin, Berlin, 1000

来源：

STATISTICS IN MEDICINE | 1993年 / 12卷 / 23期

关键词：

D O I：

10.1002/sim.4780122305

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Chance-corrected measures of agreement are prone to exhibit paradoxical and counter-intuitive results when used as measures of reliability. It is demonstrated that these problems arise with Cohen's kappa as well as with Aickin's alpha. They are the consequence of an analogy to Simpson's paradox in mixed populations. It is further shown that chance-corrected measures of agreement may yield misleading values for binary ratings. It is concluded that improvements in the design and the analysis of reliability studies are a pre-requisite for valid and pertinent results.

引用

页码：2191 / 2205

页数：15

共 33 条

[1] A MODEL FOR AGREEMENT BETWEEN RATINGS ON AN ORDINAL SCALE [J].