Given the potential value of reliability generalization (RG) studies in the development of cumulative psychometric knowledge, the purpose of this paper is to provide a tutorial on how to conduct such studies and to serve as a guide for researchers wishing to use this methodology. After some brief comments on classical test theory, the paper provides a practical framework for structuring an RG study, including: (1) test selection with an eye toward frequency of test use and reporting practices by authors; (2) development of a coding sheet that will capture potential variation in score reliability across studies; (3) procedural recommendations regarding data collection; (4) identification and use of potential dependent variables; and (5) application of general linear model analyses to the data. (Contains 40 references.) (SLD)