This paper provides an empirical comparison between utility-maximization and regret-minimization perspectives of spatial-choice behaviour. The key difference between these two perspectives is that the regret-minimization perspective implies that the anticipated satisfaction associated with a chosen spatial alternative depends on the anticipated performance of nonchosen alternatives. In order to provide a meaningful statistical comparison, we formulate a model of regret minimization such that it reduces to utility maximization for a given parameter restriction. Estimation results, based on a binary stated travel-mode-choice experiment, show how the regret-based model outperforms its utilitarian counterpart. Furthermore it is shown how participants in the experiment attached relatively much weight to the situation where the nonchosen alternative is slightly better than the chosen one, and they tend to discount larger differences. We show how this concavity of the regret function is in line with the prospect theoretical notion of risk-seeking behaviour in the domain of losses.