Income inequality decomposition using a finite mixture of log-normal distributions: A Bayesian approach
Michel Lubrano () and
Abdoul Aziz Junior Ndoye ()
Additional contact information
Abdoul Aziz Junior Ndoye: GREQAM - Groupement de Recherche en Économie Quantitative d'Aix-Marseille - ECM - Ecole Centrale de Marseille - CNRS - Centre National de la Recherche Scientifique - AMU - Aix Marseille Université - EHESS - École des hautes études en sciences sociales
Post-Print from HAL
The log-normal distribution is convenient for modelling the income distribution, and it offers an analytical expression for most inequality indices that depends only on the shape parameter of the associated Lorenz curve. A decomposable inequality index can be implemented in the framework of a finite mixture of log-normal distributions so that overall inequality can be decomposed into within-subgroup and between-subgroup components. Using a Bayesian approach and a Gibbs sampler, a Rao-Blackwellization can improve inference results on decomposable income inequality indices. The very nature of the economic question can provide prior information so as to distinguish between the income groups and construct an asymmetric prior density which can reduce label switching. Data from the \UK\ Family Expenditure Survey (FES) (1979 to 1996) are used in an extended empirical application.
Keywords: Label; switching (search for similar items in EconPapers)
Note: View the original document on HAL open archive server: https://hal-amu.archives-ouvertes.fr/hal-01440303
References: Add references at CitEc
Citations: Track citations by RSS feed
Published in Computational Statistics & Data Analysis, 2016, 100, pp.830--846. 〈10.1016/j.csda.2014.10.009〉
There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.
Journal Article: Income inequality decomposition using a finite mixture of log-normal distributions: A Bayesian approach (2016)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-01440303
Access Statistics for this paper
More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().