USING MIXTURE-MODELS IN TEMPERAMENT RESEARCH

Temperamental characteristics can be conceptualised as continuous dime nsions or qualitative categories. The continuous versus categorical qu estion concerns the underlying temperamental characteristics and not t he measured variables, which can be recorded in either continuous or c ategorical forms. This paper argues for a categorical conceptualisatio n of temperamental characteristics and applies a finite mixture model appropriate to this view to two sets of longitudinal observations of i nfants and young children. This statistical approach provides a good d escription of the observed predictive relation between behavioural pro files of children at 4 months and the degree of behavioural signs of f ear at 14 months. An advantage of the mixture model approach to this d ata, relative to more standard approaches to developmental data, is th at because it takes into account an a-priori theory, it can be used to address improvements and refinements to theories and experimental des igns in a straightforward manner.