Premium
RELATIVE INEQUALITY, ABSOLUTE INEQUALITY, AND WELFARE: LARGE SAMPLE TESTS FOR PARTIAL ORDERS
Author(s) -
Bishop John A.,
Chakraborti S.,
Thistle Paul D.
Publication year - 1994
Publication title -
bulletin of economic research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.227
H-Index - 29
eISSN - 1467-8586
pISSN - 0307-3378
DOI - 10.1111/j.1467-8586.1994.tb00577.x
Subject(s) - lorenz curve , inequality , welfare , economics , dominance (genetics) , mathematics , econometrics , intersection (aeronautics) , inference , sample (material) , stochastic dominance , distribution (mathematics) , income distribution , partial equilibrium , statistics , economic inequality , gini coefficient , microeconomics , general equilibrium theory , computer science , geography , mathematical analysis , biochemistry , chemistry , cartography , chromatography , artificial intelligence , market economy , gene
ARSTRACT Two general welfare criteria, mean‐relative Lorenz and mean‐absolute Lorenz dominance, induce partial orders on income distributions. We propose asymptotically distribution‐free inference procedures, based on the union‐intersection principle, for these two welfare criteria. Unlike classical tests, our procedures allow one to distinguish among dominance, equality, and noncomparability. We show that union‐intersection tests must be used to test for partial orders, and that the statistical ordering is acyclic. The tests are applied to compare the UK distribution of real family income to five other countries.