Interactive discrete choice models

Abstract

The interaction among the criteria plays an integral part in the human decision making process. We propose new logit models of discrete choice to give the choice probability, taking into consideration the interaction among the attributes. We further extend the proposed models to also consider the complex human attitudinal character along with the interaction among the attributes. Concretely, we combine the established econometric models with Choquet integral, attitudinal Choquet integral, Choquet integral and generalized means, and generalized attitudinal Choquet integral. The proposed models of discrete choice can be seen as providing an overarching framework with the existing models as its special cases. The scope of the existing models are significantly expanded through the generation of a very wide range of choice probabilities arising in accordance with the adjustable attitudinal parameter(s).