Departament de Psicologia | Universitat Rovira i Virgili |
Solomon Method |
Exploratory and confirmatory factor analyses are two important consecutive steps in an overall analysis process. To carry out the analyses, researchers usually collect a single sample, and then split it into two halves. As no specific splitting methods have been proposed to date in the context of factor analysis, researchers use a random split approach. However, random splitting can provide samples that are clearly not equivalent. Of course, random splitting could be used a number of times until equivalent subsamples are obtained. It must be said that this approach is not optimal from the point of view of computing time. We propose Solomon as a method to split samples into equivalent subsamples similar to one method that has already been proposed in the context of multivariate regression analysis. We implemented Solomon method in three different statistical programs:
|