ANALYSIS AND DESIGN OF MULTITRAIT-MULTIRATER PERFORMANCE-APPRAISAL STUDIES

Becker and Cote (1994) found that the correlated uniqueness model outp erformed the confirmatory factor analysis and direct product models fo r multitrait-multimethod data. The present study analyzed 20 multitrai t-multirater performance appraisal matrices. The correlated uniqueness model was appropriate significantly more often than in Pecker and Cot e's study and the other two models performed poorly. The proportions o f trait and method variance in ratings were related to several rating system characteristics such as opportunity for raters to observe ratee s and basing rating dimensions on a job analysis. Performance of all t hree models was better with larger proportions of trait variance and s maller proportions of method variance.