This paper introduces an innovative approach for detecting a sub optimal partition starting from the dendrogram produced by a hierarchical clustering technique. The approach exploits permutation tests and it can be used regard less of the agglomeration method and distance measure used in the classification process because it relies on the same criteria used for producing it. Moreover, the proposed approach can detect partitions not necessarily identiable using a traditional cut approach, as the resulting clusters could correspond to different heights of the tree.
Cutting the dendrogram through permutation tests / Bruzzese, Dario; Vistocco, D.. - ELETTRONICO. - (2010), pp. 847-854. (Intervento presentato al convegno COMPSTAT 2010. 19th International Conference on Computational Statistics tenutosi a Parigi nel 22-27 Agosto 2010) [10.1007/978-3-7908-2604-3].
Cutting the dendrogram through permutation tests
BRUZZESE, DARIO;Vistocco D.
2010
Abstract
This paper introduces an innovative approach for detecting a sub optimal partition starting from the dendrogram produced by a hierarchical clustering technique. The approach exploits permutation tests and it can be used regard less of the agglomeration method and distance measure used in the classification process because it relies on the same criteria used for producing it. Moreover, the proposed approach can detect partitions not necessarily identiable using a traditional cut approach, as the resulting clusters could correspond to different heights of the tree.File | Dimensione | Formato | |
---|---|---|---|
BruzzeseVistocco_Paper_211.pdf
non disponibili
Tipologia:
Documento in Post-print
Licenza:
Accesso privato/ristretto
Dimensione
1.18 MB
Formato
Adobe PDF
|
1.18 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.