Artigo em revista científica Q2
A bootstrap-based aggregate classifier for model-based clustering
José G. Dias (Dias, J. G.); Jeroen K. Vermunt (Vermunt, J. K.);
Título Revista
Computational Statistics
Ano (publicação definitiva)
2008
Língua
Inglês
País
Alemanha
Mais Informação
Web of Science®

N.º de citações: 33

(Última verificação: 2024-03-28 12:07)

Ver o registo na Web of Science®


: 2.9
Scopus

N.º de citações: 33

(Última verificação: 2024-03-27 19:00)

Ver o registo na Scopus


: 2.1
Google Scholar

N.º de citações: 50

(Última verificação: 2024-03-28 19:41)

Ver o registo no Google Scholar

Abstract/Resumo
In model-based clustering, a situation in which true class labels are unknown and that is therefore also referred to as unsupervised learning, observations are typically classified by the Bayes modal rule. In this study, we assess whether alternative classifiers from the classification or supervised-learning literature—developed for situations in which class labels are known—can improve the Bayes rule. More specifically, we investigate the performance of bootstrap-based aggregate (bagging) rules after adapting these to the model-based clustering context. It is argued that specific issues, such as the label-switching problem, have to be carefully addressed when using bootstrap methods in model-based clustering. Our two Monte Carlo studies show that classification based on the Bayes rule is rather stable and difficult to improve by bootstrap-based aggregate rules, even for sparse data. An empirical example illustrates the various approaches described in this paper.
Agradecimentos/Acknowledgements
--
Palavras-chave
Classification rules,Classifiers,Bootstrap estimation,Model-based clustering,Latent class model
  • Matemáticas - Ciências Naturais