A multivariate extension to cluster-weighted modeling that can deal with multivariate response is proposed. An expectation-maximization algorithm for maximum estimation of the parameters in the model is presented. A parsimonious family of models is also proposed using an eigen-decomposed covariance structure.
Cluster-weighted models for multivariate response and extensions
INGRASSIA, Salvatore;
2013-01-01
Abstract
A multivariate extension to cluster-weighted modeling that can deal with multivariate response is proposed. An expectation-maximization algorithm for maximum estimation of the parameters in the model is presented. A parsimonious family of models is also proposed using an eigen-decomposed covariance structure.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
Dang_Ingrassia_McNicholas_Browne_Cladag2013.pdf
solo gestori archivio
Licenza:
Non specificato
Dimensione
1.54 MB
Formato
Adobe PDF
|
1.54 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.