Abstract
Measurement of statistical and psychological knowledge integration. In an empirical study carried out in a Psychology experimental design class, three groups of university students completed three types of exercises: calculus, abstract, or exercises on real experimental descriptions. The three groups received the same theoretical lectures and were matched in every respect. In this context we attempted a comparison between multidimensional scaling and pathfinder on the one hand, and a new application of the generalized partial credit model. The result showed that the generalized partial credit model was the best mean to detect significant differences before and after the academic training. The results are discussed in terms of the possibility of transfer among different knowledge domains.
