On the class of attitudinal discrete choice models

Abstract

The complex human attitudinal character plays an important role in the real world decision making. To this end, we present a family of extended probabilistic discrete choice models. The attitude-based variants of multinomial logit, probit, nested, and mixed multinomial models are presented. The proposed models are further empowered through their generalization leading to a host of exponential attitudinal discrete choice models. It is shown that the existing models are the special cases of the proposed models that allow to generate a very wide range of choice probabilities in accordance with the adjustable parameter(s). The usefulness of the proposed models in modelling a decision-maker’s decision model is shown in a sequel paper.