Mixtures of factor analyzers are becoming more and more popular in the area of model based clustering of high-dimensional data. In data modeling, according to the likelihood approach, it is well known that the loglikelihood function may present spurious maxima and singularities and this is due to specific patterns of the estimated covariance structure. To reduce such drawbacks, we propose a constrained procedure which maintains the eigenvalues of the covariance structure into suitable ranges. Applications of this approach in robust clustering is then outlined

Greselin, F., Ingrassia, S. (2012). Constrained EM algorithms for Gaussian mixtures of factor analyzers. In A. Colubi, C. Croux, E.J. Kontoghiorghes, H.K. Van Dijk (a cura di), Proceedings of the 5th International Conference of the ERCIM WG on Computing & Statistics (ERCIM'12) (pp. 34-34). ERCIM WG on Computing & Statistics.

Constrained EM algorithms for Gaussian mixtures of factor analyzers

Greselin, F;
2012

Abstract

Mixtures of factor analyzers are becoming more and more popular in the area of model based clustering of high-dimensional data. In data modeling, according to the likelihood approach, it is well known that the loglikelihood function may present spurious maxima and singularities and this is due to specific patterns of the estimated covariance structure. To reduce such drawbacks, we propose a constrained procedure which maintains the eigenvalues of the covariance structure into suitable ranges. Applications of this approach in robust clustering is then outlined
Capitolo o saggio
Constrained estimation; Factor Analyzers Modeling; Mixture Models; Model-Based Clustering
English
Proceedings of the 5th International Conference of the ERCIM WG on Computing & Statistics (ERCIM'12)
Colubi, A; Croux, C; Kontoghiorghes, EJ; Van Dijk, HK
2012
978-84-937822-2-1
ERCIM WG on Computing & Statistics
34
34
E527
Greselin, F., Ingrassia, S. (2012). Constrained EM algorithms for Gaussian mixtures of factor analyzers. In A. Colubi, C. Croux, E.J. Kontoghiorghes, H.K. Van Dijk (a cura di), Proceedings of the 5th International Conference of the ERCIM WG on Computing & Statistics (ERCIM'12) (pp. 34-34). ERCIM WG on Computing & Statistics.
open
File in questo prodotto:
File Dimensione Formato  
GI Ercim 2012 Constrained EM algorithms for Gaussian mixtures of factor analyzers.pdf

accesso aperto

Dimensione 201.39 kB
Formato Adobe PDF
201.39 kB 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/10281/45068
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact