Sampling And Factor Transformation

Given a population simple structure configuration for a set of data, factor transformation methods can be compared in terms of their ability--with samples drawn from this population--to approximate closely the parameter pattern, and to do so with little sampling variability. A study is reported in which populations of factorially simple and complex data were generated with first the oblique and orthogonal factor models, and then solutions based on several special cases of the general orthomax criterion were compared on the basis of these characteristics. The result are discussed and certain practical implications noted.