A data driven equivariant approach to constrained Gaussian mixture modeling

Roberto Rocci, Stefano Antonio Gattone and Roberto Di Mari ()
Additional contact information
Stefano Antonio Gattone: Università G. d’Annunzio Chieti-Pescara
Roberto Di Mari: University of Catania

Advances in Data Analysis and Classification, 2018, vol. 12, issue 2, No 4, 235-260

Abstract: Abstract Maximum likelihood estimation of Gaussian mixture models with different class-specific covariance matrices is known to be problematic. This is due to the unboundedness of the likelihood, together with the presence of spurious maximizers. Existing methods to bypass this obstacle are based on the fact that unboundedness is avoided if the eigenvalues of the covariance matrices are bounded away from zero. This can be done imposing some constraints on the covariance matrices, i.e. by incorporating a priori information on the covariance structure of the mixture components. The present work introduces a constrained approach, where the class conditional covariance matrices are shrunk towards a pre-specified target matrix $$\varvec{\varPsi }.$$ Ψ . Data-driven choices of the matrix $$\varvec{\varPsi },$$ Ψ , when a priori information is not available, and the optimal amount of shrinkage are investigated. Then, constraints based on a data-driven $$\varvec{\varPsi }$$ Ψ are shown to be equivariant with respect to linear affine transformations, provided that the method used to select the target matrix be also equivariant. The effectiveness of the proposal is evaluated on the basis of a simulation study and an empirical example.

Keywords: Model based clustering; Gaussian mixture models; Equivariant estimators; 62H30; 62-07 (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://link.springer.com/10.1007/s11634-016-0279-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advdac:v:12:y:2018:i:2:d:10.1007_s11634-016-0279-1

Ordering information: This journal article can be ordered from
http://www.springer. ... ds/journal/11634/PS2

DOI: 10.1007/s11634-016-0279-1

Access Statistics for this article

Advances in Data Analysis and Classification is currently edited by H.-H. Bock, W. Gaul, A. Okada, M. Vichi and C. Weihs

More articles in Advances in Data Analysis and Classification from Springer, German Classification Society - Gesellschaft für Klassifikation (GfKl), Japanese Classification Society (JCS), Classification and Data Analysis Group of the Italian Statistical Society (CLADAG), International Federation of Classification Societies (IFCS)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().