Multivariate methods were used to identify between-set factors relating the criterion set of eleven Wechsler Adult Intelligence Scale Revised subtest variables to the predictor set of demographic variables: age, race, sex, education, occupation, geographic region, and urban versus rural residence. Although factor analysis is usually used to identify within-set factors, results from this method were used in comparison to those from canonical correlation, or multivariate analysis. Canonical correlation analysis was used with applications of three different orthogonal (varimax criterion) rotation strategies: (1) simultaneous, symmetrical, and joint rotation of two sets of related factors; (2) an asymmetrical rotation of each set's correlations to its canonical variates; and (3) simultaneous, symmetrical rotation of a single composite set of factors. The results from the factor analysis, the symmetrical rotation, and the asymmetrical rotation were not as helpful as the third strategy for identifying and interpreting between set factors. References and tables are appended. (Author/GDC)