Penalized factor mixture analysis for variable selection in clustered data

  title={Penalized factor mixture analysis for variable selection in clustered data},
  author={Giuliano Galimberti and Angela Montanari and Cinzia Viroli},
  journal={Computational Statistics & Data Analysis},
A model-based clustering approach which contextually performs dimension reduction and variable selection is presented. Dimension reduction is achieved by assuming that the data have been generated by a linear factor model with latent variables modeled as Gaussianmixtures. Variable selection is performed by shrinking the factor loadings though a penalized likelihood method with an L1 penalty. A maximum likelihood estimation procedure via the EM algorithm is developed and a modified BIC criterion… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 29 references

The EM algorithm for mixture of factor analyzers.í

  • Z. Ghahramani, G. E. Hilton
  • Technical Report CRG-TR-96-1,
  • 1997
Highly Influential
3 Excerpts

Variable selection using MM algorithms

  • J. Chen
  • The Annals of Statistics
  • 2007
1 Excerpt

Similar Papers

Loading similar papers…