PLS Approach for clusterwise linear regression on functional data

Preda, Cristian; Saporta, Gilbert

Document type :

Partie d'ouvrage

DOI :

10.1007/978-3-642-17103-1_17

Title :

PLS Approach for clusterwise linear regression on functional data

Author(s) :

Preda, Cristian [Auteur]

MOdel for Data Analysis and Learning [MODAL]
Saporta, Gilbert [Auteur]
CEDRIC. Méthodes statistiques de data-mining et apprentissage [CEDRIC - MSDMA]

Scientific editor(s) :

D.Banks

Book title :

Classification, Clustering, and Data Mining Applications

Publisher :

Springer
Springer Berlin Heidelberg

Publication place :

Berlin, Heidelberg

Publication date :

2004-01-01

HAL domain(s) :

Mathématiques [math]/Statistiques [math.ST]

English abstract : [en]

Partial Least Squares approach is used for the clusterwise linear regression algorithm when the set of predictor variables forms a L2 continuous stochastic process.The number of clusters is treated as unknown and the ...
Show more >Partial Least Squares approach is used for the clusterwise linear regression algorithm when the set of predictor variables forms a L2 continuous stochastic process.The number of clusters is treated as unknown and the convergence of the clusterwise algorithm is discussed.The approach is compared with other methods via an application on stock-exchange data.Show less >

Language :

Anglais

Audience :

Non spécifiée

Popular science :

Non

Comment :

IXth Conference of the International Federation of Classification Societies

Collections :