The Data Box and Within-Subject Analyses: A Comment on Nesselroade and Molenaar (2016).

Nesselroade and Molenaar suggest that it is the relationships between latent variables within subjects that are invariant across subjects and thus the appropriate unit of analysis. We disagree and take the view that between-factor correlations may differ systematically across subjects. Further, individual differences in these correlations may be an important source of information about each unique individual. Following from this premise, analyses of consistencies and differences between subjects of the within-subject pattern of interfactor correlations is a step toward an integrative science of behavior. We give several examples demonstrating how this approach has the potential to yield novel insights into personality functioning.