Empirical Welfare Analysis for Discrete Choice: Some New Results

Résumé

We develop methods of empirical welfare analysis in multinomial choice settings, under completely general consumer heterogeneity and income effects. Our results pertain to three practically important scenarios, viz., (i) simultaneous price-change of multiple alternatives, (ii) introduction/elimination of a choice-alternative, and (iii) choice among non-exclusive options. These do not follow from the single price change results of Bhattacharya (Econometrica, 2015). In program evaluation contexts, they enable estimation of compensated program effects, i.e., how much the subjects themselves value a policy intervention, and the resulting deadweight loss. Welfare analysis under endogeneity is briefly discussed.