Abstract
A method of components analysis, related to principal components analysis, is described for applications in multivariate cross-sectional or longitudinal data. The method may be useful to researchers seeking to reduce the number of observed variables through scale construction. The method creates component variables as weighted sums of the observed variables using weights that are identical across groups and occasions. The statistical and conceptual properties of these components are discussed. The method is contrasted with traditional principal components analysis and factor analysis. An application of the method is presented using longitudinal WAIS and WAIS-R data.