Detecting attribute by covariate interactions in discrete choice model

This paper introduces a simple way to identify attribute by covariate interactions in discrete choice models. This is important because modelling such interactions is an effective way to account for systematic taste variation or preference heterogeneity across different consumers. Using a simulated data set to mimic a well-known phenomenon of selective attention to design attributes, we tested our proposed approach in the banking service context. Our proposed approach was successful in detecting the attribute by covariate interactions implied by the data generation process and was found to outperform both full and stepwise interaction models. Such findings have implications for both academics and practitioners of the marketing research community in general and choice modelling field in particular.