Title: Estimation of well-clustered structure via penalized maximum likelihood method in factor analysis model
Authors: Kei Hirose - Kyushu University (Japan) [presenting]
Yoshikazu Terada - Osaka University; RIKEN (Japan)
Abstract: A prenet (PRoduct Elastic NET) penalization is proposed to estimate a well-clustered structure in a factor analysis model. The penalty is constructed by the product of a pair of parameters in each row of the loading matrix. A remarkable feature of the prenet is that a large amount of penalization leads to the perfect simple structure, which is completely well-clustered. Furthermore, the perfect simple structure estimation via the prenet penalty is shown to be a generalization of the k-means variables clustering. On the other hand, with a mild amount of prenet penalization, the estimated loading matrix is approximated by that obtained using the quartimin rotation, a widely used oblique rotation method. The proposed procedure is available for use in the R package fanc, which is available at http://cran.r-project.org/web/packages/fanc.