PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT

Detalhes bibliográficos
Autor(a) principal: Seidel, Enio Júnior
Data de Publicação: 2012
Outros Autores: Oliveira, Marcelo Silva de, Tavares, Bruno, Antonialli, Luis Marcelo
Tipo de documento: Artigo
Idioma: por
Título da fonte: Sistemas & Gestão
Texto Completo: https://www.revistasg.uff.br/sg/article/view/V7N1A6
Resumo: The investigation of similarity patterns between companies can be accomplished by the formation of similarity groups. However, there is always doubt about the best way to build clusters. Thus, the objective of this work was to study some clustering methods and some possible group sizes, so as to obtain a good clustering. In addition, an index for evaluating the clusters formed was proposed. Six clustering methods and three group sizes were considered. After the application of cluster analysis, the groups formed were assessed by the discriminant analysis, the Kappa coefficient and an index developed to assess the initial clusters. Overall, it was found that the best option would be to apply the MW method with three groups and after, to apply the discriminant analysis to obtain an appropriate final number of companies per group. This procedure allowed obtaining groups relatively similar in terms of number of elements per group. Furthermore, an interesting alternative is to make use of the index for assessing initial clusters to select the clustering method to be used, allowing selecting the best procedure.
id UFF-13_beca8a85db80a3d2a3727ed184a80fa2
oai_identifier_str oai:ojs.www.revistasg.uff.br:article/151
network_acronym_str UFF-13
network_name_str Sistemas & Gestão
repository_id_str
spelling PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENTPROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENTProcedimento para Formação de Grupos de Empresas e para Construção de Índice de Avaliação dos AgrupamentosCluster AnalysisDiscriminant AnalysisGroup SizesIndex for Evaluating ClustersCluster AnalysisDiscriminant AnalysisGroup SizesIndex for Evaluating ClustersAnálise de agrupamentosAnálise discriminanteTamanhos de grupos&Iacutendice de avaliação dos agrupamentos.The investigation of similarity patterns between companies can be accomplished by the formation of similarity groups. However, there is always doubt about the best way to build clusters. Thus, the objective of this work was to study some clustering methods and some possible group sizes, so as to obtain a good clustering. In addition, an index for evaluating the clusters formed was proposed. Six clustering methods and three group sizes were considered. After the application of cluster analysis, the groups formed were assessed by the discriminant analysis, the Kappa coefficient and an index developed to assess the initial clusters. Overall, it was found that the best option would be to apply the MW method with three groups and after, to apply the discriminant analysis to obtain an appropriate final number of companies per group. This procedure allowed obtaining groups relatively similar in terms of number of elements per group. Furthermore, an interesting alternative is to make use of the index for assessing initial clusters to select the clustering method to be used, allowing selecting the best procedure.The investigation of similarity patterns between companies can be accomplished by the formation of similarity groups. However, there is always doubt about the best way to build clusters. Thus, the objective of this work was to study some clustering methods and some possible group sizes, so as to obtain a good clustering. In addition, an index for evaluating the clusters formed was proposed. Six clustering methods and three group sizes were considered. After the application of cluster analysis, the groups formed were assessed by the discriminant analysis, the Kappa coefficient and an index developed to assess the initial clusters. Overall, it was found that the best option would be to apply the MW method with three groups and after, to apply the discriminant analysis to obtain an appropriate final number of companies per group. This procedure allowed obtaining groups relatively similar in terms of number of elements per group. Furthermore, an interesting alternative is to make use of the index for assessing initial clusters to select the clustering method to be used, allowing selecting the best procedure.A investigação de padrões de semelhança entre empresas pode ser realizada através da construção de grupos por similaridade. Contudo, geralmente se tem dúvidas quanto à melhor forma de construir os agrupamentos. Desse modo, tem-se o objetivo de estudar alguns métodos de agrupamentos e alguns possíveis tamanhos de grupos, de maneira a se obter um bom agrupamento. Além disso, se propõe um índice de avaliação dos agrupamentos formados. Consideraram-se seis métodos de agrupamentos e três tamanhos de grupos. Após a aplicação da análise de agrupamentos, foi realizada a avaliação dos agrupamentos formados através da análise discriminante, do coeficiente de concordância Kappa e de um índice desenvolvido para avaliar os agrupamentos iniciais. De forma geral, verificou-se que a melhor possibilidade seria aplicar o método MW com três grupos e, após, aplicar a análise discriminante até obter um número final adequado de empresas por grupo. Com este procedimento se obtêm grupos relativamente semelhantes em termos de número de elementos por grupo. Além disso, uma alternativa interessante é tomar uso do índice de avaliação dos agrupamentos iniciais para a escolha do método de agrupamento a ser utilizado, permitindo fazer a opção pelo melhor procedimento.ABEC2012-07-16info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/otherapplication/pdfhttps://www.revistasg.uff.br/sg/article/view/V7N1A610.7177/sg.2012.V7.N1.A6Sistemas & Gestão; v. 7 n. 1 (2012): Março/2012; 93-1021980-516010.7177/sg.2012.v7.n1reponame:Sistemas & Gestãoinstname:Universidade Federal Fluminense (UFF)instacron:UFFporhttps://www.revistasg.uff.br/sg/article/view/V7N1A6/V7N1A6Copyright (c) 2015 Sistemas & Gestãoinfo:eu-repo/semantics/openAccessSeidel, Enio JúniorOliveira, Marcelo Silva deTavares, BrunoAntonialli, Luis Marcelo2023-01-09T18:18:56Zoai:ojs.www.revistasg.uff.br:article/151Revistahttps://www.revistasg.uff.br/sgPUBhttps://www.revistasg.uff.br/sg/oai||sg.revista@gmail.com|| periodicos@proppi.uff.br1980-51601980-5160opendoar:2023-01-09T18:18:56Sistemas & Gestão - Universidade Federal Fluminense (UFF)false
dc.title.none.fl_str_mv PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
Procedimento para Formação de Grupos de Empresas e para Construção de Índice de Avaliação dos Agrupamentos
title PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
spellingShingle PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
Seidel, Enio Júnior
Cluster Analysis
Discriminant Analysis
Group Sizes
Index for Evaluating Clusters
Cluster Analysis
Discriminant Analysis
Group Sizes
Index for Evaluating Clusters
Análise de agrupamentos
Análise discriminante
Tamanhos de grupos
&Iacute
ndice de avaliação dos agrupamentos.
title_short PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
title_full PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
title_fullStr PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
title_full_unstemmed PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
title_sort PROCEDURE FOR THE FORMATION OF GROUPS OF COMPANIES AND FOR BUILDING THE INDEX FOR CLUSTER ASSESSMENT
author Seidel, Enio Júnior
author_facet Seidel, Enio Júnior
Oliveira, Marcelo Silva de
Tavares, Bruno
Antonialli, Luis Marcelo
author_role author
author2 Oliveira, Marcelo Silva de
Tavares, Bruno
Antonialli, Luis Marcelo
author2_role author
author
author
dc.contributor.author.fl_str_mv Seidel, Enio Júnior
Oliveira, Marcelo Silva de
Tavares, Bruno
Antonialli, Luis Marcelo
dc.subject.por.fl_str_mv Cluster Analysis
Discriminant Analysis
Group Sizes
Index for Evaluating Clusters
Cluster Analysis
Discriminant Analysis
Group Sizes
Index for Evaluating Clusters
Análise de agrupamentos
Análise discriminante
Tamanhos de grupos
&Iacute
ndice de avaliação dos agrupamentos.
topic Cluster Analysis
Discriminant Analysis
Group Sizes
Index for Evaluating Clusters
Cluster Analysis
Discriminant Analysis
Group Sizes
Index for Evaluating Clusters
Análise de agrupamentos
Análise discriminante
Tamanhos de grupos
&Iacute
ndice de avaliação dos agrupamentos.
description The investigation of similarity patterns between companies can be accomplished by the formation of similarity groups. However, there is always doubt about the best way to build clusters. Thus, the objective of this work was to study some clustering methods and some possible group sizes, so as to obtain a good clustering. In addition, an index for evaluating the clusters formed was proposed. Six clustering methods and three group sizes were considered. After the application of cluster analysis, the groups formed were assessed by the discriminant analysis, the Kappa coefficient and an index developed to assess the initial clusters. Overall, it was found that the best option would be to apply the MW method with three groups and after, to apply the discriminant analysis to obtain an appropriate final number of companies per group. This procedure allowed obtaining groups relatively similar in terms of number of elements per group. Furthermore, an interesting alternative is to make use of the index for assessing initial clusters to select the clustering method to be used, allowing selecting the best procedure.
publishDate 2012
dc.date.none.fl_str_mv 2012-07-16
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/other
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://www.revistasg.uff.br/sg/article/view/V7N1A6
10.7177/sg.2012.V7.N1.A6
url https://www.revistasg.uff.br/sg/article/view/V7N1A6
identifier_str_mv 10.7177/sg.2012.V7.N1.A6
dc.language.iso.fl_str_mv por
language por
dc.relation.none.fl_str_mv https://www.revistasg.uff.br/sg/article/view/V7N1A6/V7N1A6
dc.rights.driver.fl_str_mv Copyright (c) 2015 Sistemas & Gestão
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2015 Sistemas & Gestão
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv ABEC
publisher.none.fl_str_mv ABEC
dc.source.none.fl_str_mv Sistemas & Gestão; v. 7 n. 1 (2012): Março/2012; 93-102
1980-5160
10.7177/sg.2012.v7.n1
reponame:Sistemas & Gestão
instname:Universidade Federal Fluminense (UFF)
instacron:UFF
instname_str Universidade Federal Fluminense (UFF)
instacron_str UFF
institution UFF
reponame_str Sistemas & Gestão
collection Sistemas & Gestão
repository.name.fl_str_mv Sistemas & Gestão - Universidade Federal Fluminense (UFF)
repository.mail.fl_str_mv ||sg.revista@gmail.com|| periodicos@proppi.uff.br
_version_ 1798320142759755776