Decision models or descriptive models?

This paper contrasts a classic example of a logit decision model with a widely used descriptive model, the Dirichlet. Decision modeling, reviewed by Leeflang and Wittink in this issue of IJRM, aims to help make marketing-mix decisions. However, we have serious doubts about this sort of modeling: its inputs, its outputs, its assumed causality, and its frequent lack of empirically grounded predictability. It also seems to seldom really take account of already well-established marketing knowledge. In contrast, descriptive modeling more simply aims to depict actual or potential marketing knowledge, and to apply it. Such modeling often deals with marketing-mix factors separately instead of attempting to do so in one overall model.