Traditional choice models assume that observable behavior results from an unspecified evaluation process of the observed individual. When it comes to the revelation of this process mere choice models rapidly meet their boundaries, as psychological factors (e.g., consumers' perception or attitudes towards products) are not directly measurable variables and therefore cannot offhand be integrated within the model structure. The causal-analytic approach offers the possibility to specify not directly measurable factors as latent variables, and can thus reasonably supplement choice models. So far, methodological approaches investigating latent variables, and traditional choice models are perceived and applied independently of one another. In this paper the possibilities of an integration of latent variables into traditional choice models is pointed out, and an introduction into the modeling of hybrid choice models is provided. Furthermore, potential areas of application in marketing research are outlined.
Hybrid choice model latent variables causal model choice model