Robust Hicksian Welfare Analysis under Individual Heterogeneity

Sebastiaan Maes - Uantwerpen

Welfare effects of price changes are often estimated with cross-sections; these do not identify demand with heterogeneous consumers. We develop a theoretical method that utilizes uncompensated demand moments to construct local approximations for compensated demand moments, robust to unobserved preference heterogeneity. Our methodological contribution delivers robust approximations for average and distributional welfare estimates, extending to price indices and taxable income elasticities. Our method applies to any cross-section; we demonstrate it via UK household budget survey data. We document a stylized fact: simple non-parametric representative agent models are often less biased than complex parametric models with heterogeneity