Random regret minimization or random utility maximization: An exploratory analysis in the context of automobile fuel choice

Abstract

Interest in alternative behavioural paradigms to random utility maximisation (RUM) has existed ever since the dominance of the RUM formulation. One alternative is known as random regret minimisation (RRM), which suggests that when choosing between alternatives, decision-makers aim to minimise anticipated regret. Although the idea of regret is not new, its incorporation into the same discrete choice framework of RUM is very recent. This paper is the first to apply the RRM-model framework to model choice among durable goods. Specifically, we estimate and compare RRM- and RUM-models in a stated choice context of choosing amongst petrol, diesel and hybrid fuelled vehicles (associated with specific levels of fuel efficiency and engine capacity). The RRM-model is found to achieve a marginally better fit (using a non-nested test of differences) than its equally parsimonious RUM-counterpart. As a second contribution, we derive a formulation for regret-based elasticities, and compare utility- and regret-based elasticities in the context of stated vehicle-type choices. We find that in the context of our choice-data, mean estimates of elasticities are different for many of the attributes and alternatives.