The taxometric method is described as a means of analyzing the "latent structure" of key criminality constructs such as psychopathy. "Latent structure" is some feature of an entity (an offender in the current discussion) that cannot be directly observed (psychological characteristics) but which is important in distinguishing an entity (offender) from another entity (another offender). Although the latent structure of a construct cannot be directly observed, it can be inferred from observable or measurable manifestations ("manifest structure") of the latent structure. The process of such measurement depends on determining whether the latent structure is "categorical," "dimensional," or a mixture of both. Categorical latent structure means that the construct divides entities into distinct groups or categories (qualitative difference). Dimensional latent structure, on the other hand, means that the construct orders entities along a continuum of scores or levels (e.g., degree of delinquency) or quantitative difference. In contrast to the dimensional-leaning biases of factor analysis and the categorical-leaning biases of data clustering, Paul Meehl's taxometric method, when properly implemented, favors neither categories or dimensions. Meehl initially designed the taxometric method to test for a schizoid (predisposition to schizophrenia) taxon. Since that time, it has evolved to become one of the more popular procedures for assessing latent structure type (category vs. dimension). This paper presents taxometric principles, preconditions for taxometric analysis, taxometric procedures, and an example of how the taxometric method can be applied to criminal justice data. 2 tables, 6 figures, and 69 references