Multivariate methods are being used with increasing frequency in educational research because these methods control "experimentwise" error rate inflation, and because the methods best honor the nature of the reality to which the researcher wishes to generalize. This paper: explains the basic logic of canonical analysis; illustrates that canonical analysis is a general parametric analytic method subsuming other methods; and provides an example of one strategy that can be used to investigate the generalizability of multivariate results. Actual data from the Holzinger and Swineford (1939) study are used to contextualize the discussion. Five random samples of 301 cases were drawn from data modeled on the 10,000 cases of Holzinger and Swineford to explain the effects of sampling error. Eight tables and one figure present data, and a 49-item list of references is included. An appendix provides the Statistical Analysis System (SAS) program used. (SLD)