Two new methods for the meta-analysis of factor loadings are introduced and evaluated by Monte Carlo simulations. The direct method pools each factor loading individually, whereas the indirect method synthesizes correlation matrices reproduced from factor loadings. The results of the two simulations demonstrated that the accuracy of…

Multilevel models are often used to evaluate hypotheses about relations among constructs when data are nested within clusters (Raudenbush & Bryk, 2002), although alternative approaches are available when analyzing nested data (Binder & Roberts, 2003; Sterba, 2009). The overarching goal of this article is to suggest when it is appropriate…

The cross-cultural generalizability of vocational interest structures has received significant attention in recent years. This article adds to this research in four respects. First, data from a context that has not previously been investigated (Germany) was analyzed. Second, students at different stages of their educational career were examined.…

The "factor" analyses published by Schultz, Kaye, and Hoyer (1980) confused component and factor analysis and led to unwarranted conclusions. The principal factors method yields two factors which support the a priori expectation of a difference between intelligence tasks and spontaneous flexibility tasks. (Author/RD)

This paper is concerned with the study of similarities and differences in factor structures between different groups. A common situation is when a battery of tests has been administered to samples of examinees from several populations. A very general model is presented, in which any parameter in the factor analysis models (factor loadings, factor…

A common problem in the behavioral sciences is to determine if a set of observed variables can be more parsimoniously represented by a smaller set of derived variables. To address this problem, the performance of five methods for determining the number of components to retain (Horn's parallel analysis, Velicer's Minimum Average Partial (MAP),…

The author refutes Humphrey's test of the Spearman hypothesis. A fair test requires that Black and White samples not be selected on any g-correlated variable, including socioeconomic status. Humphrey's factor analysis on test-score means of demographic groups, rather than on individuals, inflates g loadings and biases results. (LMO)

This author reviews published data and presents new data relevant to the Spearman hypothesis concerning racial differences on cognitive tests. He concludes that across-the-board difference between SES groups occurs primarily on the general factor, and that there are major determinants of race differences independent of the general factor.…

The author responds to criticisms made by Jensen pertaining to tests of the Spearman hypothesis. The near-zero correlation between Blacks and low socio-economic status Whites is neither an artifact of methodology nor a sampling fluke. Low and high SES White differences are highly correlated with general factor loadings. (LMO)

This paper describes, by focusing on factor analytic structures, pupils' reactions towards the utilisation and preservation of nature. A previously hypothesised model based on these two domains (comprised of 5 primary factors) was shown to be valid for four different Western European pupil samples: CH, D, DK, IRL. The empirical basis of this…