Empirical versus policy equivalence scales: matching estimation

Abstract

Properties of three types of equivalence scales obtained through the matching estimations are compared. The scales are derived by estimating the effect that demographic variables have on the houshold expenditures. The types estimated include: i/ matching on common values of well-being covariates (partly normative approach), ii/ matching on simulated quivalent expenditure minimising the deviation between the estimated and persumed value (solely empirical method), iii/matching on covariates with imposed economy of scale on selected commodities (policy scales). Unlike many scales based on the estimates of demand systems, those obtained by the matching estimation confirm expectations based on the economic theory.