RELIABILITY GENERALIZATION - EXPLORING VARIANCE IN MEASUREMENT ERROR AFFECTING SCORE RELIABILITY ACROSS STUDIES

Because tests are not reliable, it is important to explore score relia bility in virtually all studies. The present article proposes and illu strates a new method-reliability generalization-that can be used in a meta-analysis application similar to validity generalization. Reliabil ity generalization characterizes (a) the typical reliability of scores for a given test across studies, (b) the amount of variability in rel iability coefficients for given measures, and (c) the sources of varia bility in reliability coefficients across studies. The use of reliabil ity generalization is illustrated here by analyzing 87 reliability coe fficients reported for the two scales of the Bem Sex Role Inventory (B SRI).