A goodness-of-fit approach to estimating equivalence scales

We use income satisfaction data in order to estimate equivalence scales. Our method differs from previous attempts to use satisfaction data for this purpose in that it can be used to estimate or evaluate any given parametric equivalence scale. It can also be employed to investigate specific questions related to equivalence scales such as whether these scales are income-dependent or to what extent they depend on specific household characteristics such as whether some household members are in a partner relationship. A further advantage of our approach is that, within a first-differencing nonlinear least-squares framework, we can carry out full statistical inference about the hypotheses under consideration. Our empirical results suggest that household economies of scale are higher than those assumed in commonly used scales such as the OECD or the Luxembourg scale. We also obtain the novel empirical result that economies of scale may decrease (rather than increase) in income, which is what one would expect if the share of consumption goods generating economies of scale (such as housing) decreases with income.