Sixteen measures of reliability for two-category nominal scales are compared. Upon correcting for chance agreement, there are only five distinct indices: Fleiss's modification of A-sub-1, the phi coefficient, Cohen's kappa, and two intraclass coefficients. Recommendations for choosing an agreement index are made based on definitions, magnitude,…

An investigation of the Conners' Teacher Rating Scale-Revised hyperactivity scale found that the referents for teacher ratings should be determined, teachers' ratings should be made more objective, standardization across teachers should be demonstrated before norms are preferred, and the rating scale should be validated via observations or other…