Connections between the basic local independence model and true and error models in the study of preference

Two classes of probabilistic models are compared: the true and error (TE) type models and models in the family of the basic local independence model (BLIM). The former finds applications in the study of human preference, whereas the latter has been developed within the theory of knowledge structures with the aim of producing knowledge assessment models. Clear analogies exist between the two approaches. The aim of the present work was to carry out a formal comparison between, the BLIM and some of the TE models. Moreover, some new results about the identifiability of the BLIM arise. In fact, the identifiability problems that are common in the application of the model to knowledge assessment can be avoided in the domain of choice if proper designs are used.