In this paper we introduce a procedure for the parameter estimation of mixtures of factor analyzers, which maximizes the likelihood function in a con- strained parameter space, to overcome the well known issue of singularities and to reduce spurious maxima of the likelihood function. A Monte Carlo study of the per- formance of the algorithm is provided. Finally the proposed approach is employed to provide a market segmentation, to model a set of quantitative variables provided by a telecom company, and related to the amount of services used by customers
Greselin, F., Ingrassia, S. (2013). Market segmentation via mixtures of constrained factor analyzers. In E. Brentari, M. Carpita (a cura di), Advances in Latent Variables : Methods, Models and Applications. SIS 2013 Statistical Conference (University of Brescia - June, 19-21 2013). Milano : Springer.
Market segmentation via mixtures of constrained factor analyzers
Greselin, F;
2013
Abstract
In this paper we introduce a procedure for the parameter estimation of mixtures of factor analyzers, which maximizes the likelihood function in a con- strained parameter space, to overcome the well known issue of singularities and to reduce spurious maxima of the likelihood function. A Monte Carlo study of the per- formance of the algorithm is provided. Finally the proposed approach is employed to provide a market segmentation, to model a set of quantitative variables provided by a telecom company, and related to the amount of services used by customers
| File | Dimensione | Formato | |
|---|---|---|---|
|
GI SIS 2013 Market segmentation.pdf
accesso aperto
Dimensione
978.21 kB
Formato
Adobe PDF
|
978.21 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
