Heterogeneous Decision Paradigms in Choice Experiment Data: A Bayesian Investigation

Discrete mixture (DM) models recognize the presence of heterogeneity across individuals in a given population. In the context of a public land use discrete choice experiment, we use DM models to allow for respondent behavior to probabilistically mix over multiple competing decision paradigms. We pairwise combine the Random Utility Model (RUM), Contextual Concavity Model (CCM), and Random Regret Minimization (RRM) paradigms into three DM models, in which the probability of an individual adhering to a particular paradigm is modeled as a function of sociodemographic characteristics. We present a comprehensive Bayesian analysis for which we explicitly describe prior selection, inferential procedures, and model comparison metrics. Using out-of-sample predictive information criteria, we find evidence that single-paradigm models are too restrictive and that the discrete mixture models are able to consistently identify two latent groups of decision makers, allowing us to refine willingness to pay estimates. For the DM models, we develop a novel algorithm to calculate wholesome willingness to pay estimates for improvements in different public park amenities in Polk County, Iowa.