Rich, Average And Poor Regions In The Czech And Slovak Republic – Model Based Clustering
Abstract
One way to analyse the actual state of economics can be done by quantitative illustration of the financial power of households. The current economical crisis has the greatest negative impact on the poorest households below the poverty threshold. Therefore, this paper focuses on quantification of the financial situation of households in individual regions in correlation with the poverty threshold. It contains description of methods used and results of their application with respect to evaluation of spatial distribution of poverty of population on the regional level in the Czech Republic and Slovakia. The methodology is based on finite mixtures of regression models that belong to methods called Model Based Clustering. It concerns special methods of clustering of objects that are based on probability models. The criterion for clustering of regions is the level of risk of poverty rate of households. The regions are divided into three clusters (components) – “rich”, “middle”, and “poor”. The households are scored according to the level of national poverty threshold, in our case according to the level 60% of median of the national equivalised disposable household income. The results of the statistical survey EU SILC (European Union – Statistics on Income and Living Conditions) made by the Czech Statistical Office and the Statistical Office of the Slovak Republic in year 2005 through 2009 form the data base. All calculations have been made in the freeware programming environment R, which is accessible on the internet (http://cran.r-project.org/). For the purpose of modelling of the poverty rate of households using the regression clusters, the upgrade package flexmix was used.References
Bartosova, Jitka, and Marie Forbelska,”Mixture Model Clustering for Household Incomes.” Aplimat – Journal of Applied Mathematics 3(2010a): 163-172.
Bartosova, Jitka, Marie Forbelska, and eds. “Comparison of Regional Monetary Poverty in the Czech and Slovak Republic.” Social Capital, Human Capital and Poverty in the Regions of Slovakia. Kosice : Technical University of Kosice, 2010b: 76-84.
Bilkova, Diana. “Analysis of the Development in Wage Distributions of Men and Women in the Czech Republic in Recent Years.” Statistika – Journal for Economy and Statistics 48.1(2011): 40-57.
Dempster, Arthur P., et al. “Likelihood from Incomplete Data via the EM Algorithm.” Journal of the Royal Statistical Society: Series B 39.1(1977): 1-38.
Forbelska, Marie, Jitka Bartosova, and eds. “Clustering of Czech Household Incomes Over Very Short Time Period.” Proceedings of COMPSTAT’2010. Paris : Physica Verlag HD, 2010: 1023-1030.
Foster, James, Joel Greer, and Erik Thorbecke. “A Class of Decomposable Poverty Measures.” Econometrica 52.3(1984): 761-766.
Jiang, Jiming. Linear and Generalized Linear Mixed Models and Their Applications. Berlin : Springer Verlag, 2007.
Jarosova, Eva, and eds. “Estimation with the Linear mixed effects model.” Proceedings of Aplimat’2010. CD-ROM. Bratislava : Slovak university of technology in Bratislava, 2010: 913–920.
Longford, Nicholas T., et al., eds. “Discussion of ‘Model-based clustering for social networks’ by Handcock, M.S., Raftery, A.E., and Tantrum, J.M.” Journal of the Royal Statistical Society: Series B 170.2(2007): 329.
Longford, Nicholas T., and M. Grazia Pittau. “Stability of household income in European countries in the 1990’s.” Computational Statistics and Data Analysis 51.2(2006): 1364-1383.
Longford, Nicholas T., and Pierpaolo D´urso. “Mixtures with an improper components.” Journal of Applied Statistics 38.11(2011): 2511-2521.
Mala, Ivana. “Conditional Distributions of Finite Mixtures of Probability Distributions.” AMSE’2011. Wroclaw : Uniwersytet Ekonomiczny, 2011a: 18.
Mala, Ivana. “Conditional Distributions of Incomes and their Characteristics.” Proceedings of ISI’2011. Dublin : ISI, 2011b: 1–6.
Marek, Lubos. “The Trend of Income Distributions in Czech Republic in the Years 1995-2008 Analysis.” Politicka ekonomie. 2010. 2(2010): 186-206.
McCullagh, Peter, and John Ashworth Nelder. Generalized Linear Models. London : Chapman and Hall, 1994.
McCulloch, Charles E., and Shayle Robert Searle. Generalized, Linear, and Mixed Models. New York : Wiley & Sons, 2001.
McLachlan, Geoffrey J., and David Peel. Finite mixture models. New York : Wiley & Sons, 2000.
Nelder, John A., and Robert William Maclagan Wedderburn. “Generalized linear models.” Journal of the Royal Statistical : Society Series A 135.3(1972): 370-384.
Pauhofova, Iveta, and eds. “Regional Income Stratification of Slovak Population.” Social Capital, Human Capital and Poverty in the Regions of Slovakia. Kosice : Technical University of Kosice, 2010: 22-30.
Stankovicova, Iveta, and eds. “Regional aspects of monetary poverty in Slovakia.” Social Capital, Human Capital and Poverty in the Regions of Slovakia. Kosice : Technical University of Kosice, 2010, 67-75.
Vecernik, Jiri. Czech Society in the 2000s: a report on socio-economic policies and structures. Praha : ACADEMIA, 2009.
Zelinsky, Tomas. “Comparison of Alternative Approaches to Estimation of Individual Welfare of Poor Households.” Ekonomicky casopis / Journal of Economics. 58. (2010a): 251-270.
Zelinsky, Tomas. “Analysis of Poverty in Slovakia Based on the Concept of Relative Deprivation.” Politicka ekonomie. 58.3(2010b): 542-565.
Copyright information
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Creative Commons Attribution License 3.0 - CC BY 3.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
