ABSTRACT
It has already been pointed out in previous chapters that the extracted factor matrix does not usually provide a suitable final solution to a factor analysis problem. Most extraction methods are designed to extract something approximating the maximum amount of variance at each step. The factors, therefore, get progressively smaller until finally they are too small for retention. At each step, variance from many different common factor sources is being extracted because the factor vector is placed in such a way that as many of the variables as possible have substantial projections on it. It is not atypical for entirely uncorrelated data vectors to have substantial projections on the same extracted factor vector. Such extracted factor vectors are, then, complex composites of partially overlapping and even unrelated data variables rather than narrowly defined factors represented by homogeneous collections of closely related data variables.
