The identification of groups’ prototypes, i.e. elements of a dataset that are representative of the group they belong to, is relevant to the tasks of clustering, classification and mixture modeling. The R package pivmet includes different methods for extracting pivotal units from a dataset, to be exploited for a Markov Chain Monte Carlo (MCMC) relabelling technique for dealing with label switching in Bayesian estimation of mixture models. Moreover, consensus clustering based on pivotal units may improve classical algorithms (e.g. k-means) by means of a careful seeding.

PIVMET: pivotal methods for Bayesian relabelling in finite mixture models

Leonardo Egidi;Roberta Pappadà;Francesco Pauli;Nicola Torelli
2021-01-01

Abstract

The identification of groups’ prototypes, i.e. elements of a dataset that are representative of the group they belong to, is relevant to the tasks of clustering, classification and mixture modeling. The R package pivmet includes different methods for extracting pivotal units from a dataset, to be exploited for a Markov Chain Monte Carlo (MCMC) relabelling technique for dealing with label switching in Bayesian estimation of mixture models. Moreover, consensus clustering based on pivotal units may improve classical algorithms (e.g. k-means) by means of a careful seeding.
978-88-5518-340-6
https://fupress.com/catalogo/cladag-2021-book-of-abstracts-and-short-papers-/7254
File in questo prodotto:
File Dimensione Formato  
Pappada_PIVMET.pdf

accesso aperto

Descrizione: contributo con frontespizio e indice del volume
Tipologia: Documento in Versione Editoriale
Licenza: Creative commons
Dimensione 15.59 MB
Formato Adobe PDF
15.59 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/2994386
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact