Measures of agreement: a single procedure

Abstract

An assessment of measurement agreement made by devices, laboratories, or raters is important in medical practice and research. The setting in which each randomly selected subject is rated by the same two raters raises assorted questions regarding rate agreement. The intraclass correlation coefficient (ICC) is one measure of reliability. The paired t-test can be used to evaluate the overall ratings or bias of the two raters, while their variances can be assessed with Pitman's test. The Bradley-Blackwood test can be used for a simultaneous test of their means and variances. A single method that provides results for these approaches is proposed and the bivariate confidence ellipse is suggested to provide boundaries for dispersion.