Because reliability is a function of scores, and not tests per se, it is inaccurate to hold that a given test will yield scores with the same reliability across samples. Therefore, score reliability should always be reported and interpreted in both measurement and substantive studies. In an effort to facilitate this outcome, this paper is intended to provide an interpretive framework for applied researchers and others seeking a conceptual understanding of score reliability. The paper reviews some basic tenets of classical test theory, discusses the salient factors that affect reliability estimates, with emphasis on coefficient alpha, and present several suggestions toward a better understanding, and improved use, of score reliability. (Contains 6 tables, 1 figure, and 43 references.) (Author/SLD)