Los puntos clave no están disponibles para este artículo en este momento.
He shall describe a computer program for simultaneously factor analyzing dispersion matrices obtained from independent groups. A common situation, when this program will be usef'u L, is when a battery of tests has been administered to samples of examinees from several populations and one wants to study similarities and differences in factor structures between the different populations. The most important feature of the program is that pararneters in the factor analysis models (factor loadings, factor variances, factor covariances, and unique variances) for the different populations may be assumed to be kno~~a priori or specified to be invariant over populations.
Thillo et al. (Tue,) studied this question.