Nonparametric Welfare Analysis for Discrete Choice: Levels and Differences of Individual and Social Welfare

Empirical welfare analyses often impose stringent parametric assumptions on individuals’ preferences and neglect unobserved preference heterogeneity. In this paper, we develop a framework to conduct individual social analysis for discrete choice that does not suffer from these drawbacks. We first adapt the broad class of measures introduced by Fleurbaey (2009) settings where is discrete. Allowing unrestricted, heterogeneity, become random variables. then show distribution objects can be derived probabilities, which estimated nonparametrically cross-sectional data. addition, derive nonparametric results joint differences, as well welfare. The former an important tool in determining whether those who benefit price change belong disproportionately were initially well-off. An empirical application illustrates methods.