Using data from four different case studies in both revealed (RP) and stated preference (SP), we compare the Random Regret Minimization (RRM) and the Random Utility  Maximization (RUM) models in terms of parameter estimates, goodness of fit, elasticities and consequential policy implications.

The first experiment presented uses data from a Stated Choice-experiment (SP) aimed at identifying valuations of characteristics of nature parks in Italy; the second is a travel cost study (RP) exploring factors that influence kayakers’ site-choice decisions in the Republic of Ireland; the third is a stated choice experiment (SP) conducted among Swiss logistics managers; and the fourth is a stated choice experiment (SP) on diet, physical activity and coronary heart disease risk, administered in Northern Ireland.

In all the experiment both the traditional Random Utility multinomial logit model (RU-MNL) and the Random Regret multinomial logit model (RR-MNL) are estimated to gain more insights into respondents’ choices. In the first and third experiments we compare RR-MNL and RU-MLN in terms of model fit, elasticities probability forecasting and consequential policy implications, while in the second and fourth experiments we further explore whether choices are driven by a utility maximization or a regret minimization paradigm by running a binary logit model to examine the likelihood of the two decision choice paradigms, using respondents and choice characteristics as explanatory variables.

Results from all studies suggest that the two approaches retrieve similar model fits estimating the same number of parameters. However, they do imply slightly different conclusions arising from the research. This begs the question of which modelling approach the researcher should apply. We would argue that, given the ease with which RR-MNL models, the analyst should consider applying both modelling approaches to their data in order to better explore the multidimensional phenomenon of decision making.