Factors in teachers' ratings of schoolchildren: Heymans' data reconstructed by modern standards

Abstract

In this article we re‐analyse the data that Heymans and Wiersma collected on pupils from secondary schools, about 80 years ago. The main interest is in the structure of the adolescence data set in terms of modern standards and understood against the background of recent findings. More specifically, one question is whether the Heymans data can be understood in terms of the framework of the Big Five structure of personality traits. To that end, principal components analysis and multiple group analysis were performed. The general conclusion from these analyses is that the adolescence data are best described by a two‐dimensional structure. Another more specific research question is to what extent Heymans' own three dimensions can be detected in the data set. With emphasis on a small number of criterion items, used by Heymans to identify the three dimensions, a three‐factor solution was inspected for this purpose. The conclusion from this analysis is that the three Heymans dimensions cannot unequivocally be identified in the adolescence data set.