Walton et al. (2011) applied dimensional, categorical, and hybrid models to analyses of CBCL and YSR scores obtained by an epidemiological sample of 2,027 Dutch youths at ages 11.1 and 13.6 years. For dimensional analyses, a latent trait model described the probability that each particular problem item would be endorsed on the basis of the youth’s level on a continuous latent trait. For categorical analyses, a latent class model categorized youths into discrete classes according to patterns of item scores. And for the hybrid analyses, a factor mixture model categorized youths into discrete classes but allowed for heterogeneity within each class with respect to the severity of scores. For both the Aggressive Behavior and Rule-Breaking Behavior syndromes, the latent trait model fit the data better than the latent class and hybrid models at ages 11.1 and 13.6, for both boys and girls. Walton et al. concluded “that classification models can be based on empirical evidence rather than a priori preferences, and while current classification systems conceptualize externalizing problems in terms of discrete groups, they can be better conceptualized as dimensions” (p. 553).
Reference: Walton, K.E., Ormel, J., & Krueger, R.F. (2011). The dimensional nature of externalizing behaviors in adolescence: Evidence from a direct comparison of categorical, dimensional, and hybrid models. Journal of Abnormal Child Psychology, 39, 553-561.