Local cover image
Local cover image

Determinants of Inequality in Selected SEE Countries: Results from Shapley Value Decompositions

By: Leitner, Sebastian.
Contributor(s): Stehrer, Robert.
Material type: materialTypeLabelBookSeries: wiiw Balkan Observatory Working Papers: 84Publisher: Wien : Wiener Institut für Internationale Wirtschaftsvergleiche (wiiw), 2009Subject(s): Inequality decomposition | Gini | Shapley value | Western Balkan countriesCountries covered: SEEClassification: C20 | D63 Online resources: Click here to access online Summary: In this paper we provide a comparative analysis of inequality in household consumption per capita in four South-Eastern European countries, Albania, Bosnia & Herzegovina, Bulgaria, and Serbia. The analysis is based on a largely consistent dataset derived from the World Bank’s Living Standards Measurement Study (LSMS) providing data for at least two years for each of these countries and a comparable set of variables. We apply inequality decomposition methods based on regression analysis and variants of the Shapley value approach. We also present results from related methods like a decomposition of the explained variance using different approaches for comparisons. The results suggest that three groups of variables are particularly important for explaining patterns of inequality; these are socio-demographic variables, employment status and education. Regional aspects and nationality or ethnicity plays a less important role though there are some country differences.

In this paper we provide a comparative analysis of inequality in household consumption per capita in four South-Eastern European countries, Albania, Bosnia & Herzegovina, Bulgaria, and Serbia. The analysis is based on a largely consistent dataset derived from the World Bank’s Living Standards Measurement Study (LSMS) providing data for at least two years for each of these countries and a comparable set of variables. We apply inequality decomposition methods based on regression analysis and variants of the Shapley value approach. We also present results from related methods like a decomposition of the explained variance using different approaches for comparisons. The results suggest that three groups of variables are particularly important for explaining patterns of inequality; these are socio-demographic variables, employment status and education. Regional aspects and nationality or ethnicity plays a less important role though there are some country differences.

Click on an image to view it in the image viewer

Local cover image
The Vienna Instiute for International Economic Studies (wiiw)

Powered by Koha