Contrasts of Relative Advantage Maximisation with Random Utility Maximisation and Regret Minimisation

This paper discusses the theoretical properties and the empirical application of an improved version of the 'relative advantage maximising' (RAM) model. This model shares several desirable features of a set of models based on random regret minimisation (RRM), such as parsimony and choice set dependence. Although model fit differences are small, a preliminary comparison shows that the RAM model empirically outperforms the standard random utility maximisation (RUM) model, the RRM model, and a hybrid RUM-RRM model in all eight data sets analysed. The paper concludes with a discussion of the marginal willingness to pay (WTP) measures derived from the RAM model.