Homogeneity of kappa statistics in multiple samples.

摘要

The measurement of intra-observer agreement when the data are categorical has been the subject of several investigators since Cohen first proposed the kappa (kappa) as a chance-corrected coefficient of agreement for nominal scales. Subsequent procedures have been developed to assess the agreement of several raters using a dichotomous classification scheme, assess majority agreement among several raters using a polytomous classification scheme, and the use of kappa as an indicator of the quality of a measurement. Further developments include inference procedures for testing the homogeneity of k>/=2 independent kappa statistics. An executable FORTRAN code for testing the homogeneity of kappa statistics (kappa(h)) across multiple sites or studies is given. The FORTRAN program listing and/or executable programs are available from the author on request.