This paper examines the history of approaches to diagnosis in education and in medicine--a profession with concentrated attention to the conceptual and mathematical underpinnings of diagnosis. Presented is a comprehensive model of diagnostic testing in education and a summary of the results of four studies, one from each of four separate heuristics developed within the model. The paper concludes with a discussion of the advantages, disadvantages, and possible productive directions for educational diagnosis, particularly in the realm of individualized adaptive diagnostic testing administered by computer. A report "Some Strategies for Constructing and Validating Diagnostic Hypotheses" is appended. (PN)