Abstract

Preferences differ in the population, and this heterogeneity may not be adequately described by observed characteristics and additive error terms. As a first contribution, this study shows that preference heterogeneity can be represented graphically by means of violations of the Weak Axiom of Revealed Preference (WARP), and that computing the minimum number of partitions necessary to break all WARP violations in the sample is equivalent to computing the chromatic number of this graph. Second, the study builds the bridge between revealed preference theory and cluster analysis to assign individuals to these partitions (i.e. preference types). The practical methods are applied to Dutch labour supply data, to recover reservation wages of individuals who belong to particular preference types.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call