Welfare Analysis using Nonseparable Models

Résumé

This paper studies the distribution of welfare effects when individual demands are characterized by a nonseparable model which is monotonic in unobserved heterogeneity. First, we provide and discuss conditions under which the heterogeneous welfare effects are identified. We then propose a sample counterpart estimator, and analyze its large sample properties. Finally, we apply all concepts to measuring the heterogeneous effect of a chance of gasoline price using US consumer data, and we find substantial differences in individual effects.