Endogeneity of Household Size and Income in the Estimation of Equivalence Scales from Satisfaction Data

Abstract

Analyses of income distributions across households crucially depend on equivalence scales. They define income increments necessary to keep a household’s living standard constant as it is joined by additional adults or children. Such scales have frequently been estimated using income satisfaction data, yet under the assumption that household income, size, and structure are exogenous. The present paper is the first to relax this assumption and consider the possible endogeneity of income and family size in income satisfaction. This involves an empirical analysis of data from the German Socio-Economic Panel (SOEP) using fixed-effects regressions with heteroscedasticity-based instruments. Our results confirm that endogeneity is relevant in regressions of income satisfaction; equivalence weights, however, appear not to be biased significantly. Accounting for endogeneity in income and family size has virtually no implications for distribution and poverty analyses.