Título: A New Clustering Procedure Applied to an International Comparison of Indebtedness
Autores: Monteiro, André d’Almeida; Carneiro, Dionísio Dias; Pedreira, Carlos Eduardo
Resumo: This paper presents a procedure for clustering analysis that combines Kohone\’s Self-organizing Feature Map (SOFM) and statistical schemes. The idea is to cluster the data in two stages: run SOFM and then minimize the segmentation dispersion. The advantages of proposed procedure will be illustrated through a synthetic experiment and a real macroeconomic problem. The procedure is then used to explore the relationship between private indebtedness and some macroeconomic variables commonly used to measure macroeconomic performance. The experiences of thirty-nine countries in the early nineties are analyzed. The procedure outperformed others clustering techniques in the job of identifying consistent groups of countries from the economic and statistical viewpoints. It found out similarities in different countries concerning their respective levels of private indebtedness when added to well-accepted parameters to measure macroeconomic performance.
Palavras-chave: Vector quantization; Clustering; Self-Organizing Feature Map; Macroeconomic Performance; Private Indebtedness
Páginas: 10
Código DOI: 10.21528/lmln-vol2-no2-art5
Artigo em PDF: vol2-no2-art5.pdf
Arquivo BibTex: vol2-no2-art5.bib