Aplicação de Data Envelopment Analysis - DEA para obtenção de mapas de exclusão e inclusão social

• Ano de defesa: 2007
• Autor(a) principal: SOUZA, Luciano
• Orientador(a): STOSIC, Borko
• Banca de defesa: CORDEIRO, Gauss Moutinho, CAVALCANTI, Helenilda Wanderlei de Vasconcelos, FITTIPALDI, Ivon Palmeira
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal Rural de Pernambuco
• Programa de Pós-Graduação: Programa de Pós-Graduação em Biometria e Estatística Aplicada
• Departamento: Departamento de Estatística e Informática
• País: Brasil
• Palavras-chave em Português: Exclusão social; Inclusão social
• Palavras-chave em Inglês: Data Envelopment Analysis; DEA; Descision Making Units; DAMUs; Social exclusion; Social inclusion
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA
• Link de acesso: http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/5162

This dissertation proposes use of Data Envelopment Analysis (DEA) as methodology to quantify the concept of social exclusion, with application to the city of Recife. The primary advantage of DEA is that, besides associating a quantitative value (index) to each of the considered geographical units (districts or census sectors, in DEA terminology Decision Making Units - DMUs), it also provides optimum levels (goals) for all the variables considered, that should be attained by each of the units in order to eliminate social exclusion. In addition, being a non-parametric method, DEA does not require introduction of any arbitrary parameters, which might compromise the analysis. Social exclusion is analyzed here considering four utopias: education, living conditions, income and equality, which are treated both individually, and all together. For each of the five considered contexts numerical values of the exclusion index, the optimum variable level, and the corresponding geographical exclusion maps, are provided for the city of Recife, on the level of districts and census sectors. Within the context of the current choice of utopias under study, and the corresponding input and output variables, these results make it possible to identify districts and census sectors that present highest and lowestvalues of the inclusion index. In particular, it is found that only 19% of the districts of the city of Recife demonstrate an optimum level of social inclusion index, while for all the other districts concrete goals for reaching social inclusion are established, within the current context. Therefore, the applied methodology fills a gap in the existing practice of analyzing social exclusion by supplying the optimum variable levels for each considered unit, which may be used for urban planning and optimization of investments.