Abstract

The distribution of income in a population consists of the different distributions in the various age groups weighted by the age structure. In using inequality statistics to measure the redistributive effect of taxation, it is desirable to remove the arbitrary effect of the age-weighting. Formulae for ‘conventional’ and for ‘correct’ indices of incidence are given, and are evaluated in a stochastic-process model that captures many features of actual income distributions. For the lognormal distribution, the direction of bias of conventional incidence indices is determined simply by writing them as functions of the lognormal dispersion parameter.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call