Latent Classes of Objects and Variable Selection

Giuliano Galimberti (), Angela Montanari () and Cinzia Viroli ()
Additional contact information
Giuliano Galimberti: University of Bologna, Statistics Department
Angela Montanari: University of Bologna, Statistics Department
Cinzia Viroli: University of Bologna, Statistics Department

A chapter in COMPSTAT 2008, 2008, pp 373-383 from Springer

Abstract: Abstract In this paper we present a model based clustering approach which contextually performs dimension reduction and variable selection. In particular we assume that the data have been generated by a linear factor model with latent variables modeled as gaussian mixtures (thus obtaining dimension reduction) and we shrink the factor loadings, resorting to a penalized likelihood method, with an L1 penalty (thus realizing automatic variable selection). We derive an EM algorithm to obtain the penalized model estimates and a modified BIC criterion to select the penalization parameter. We evaluate the performance of the proposed method on simulated data.

Keywords: factor analysis; LASSO; finite Gaussian mixtures (search for similar items in EconPapers)
Date: 2008
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:sprchp:978-3-7908-2084-3_31

Ordering information: This item can be ordered from
http://www.springer.com/9783790820843

DOI: 10.1007/978-3-7908-2084-3_31

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().