Logo image
Se connecter
Selecting models focussing on the modeller's purpose
Acte de colloque

Selecting models focussing on the modeller's purpose

Jean-Patrick Baudry, Gilles Celeux et Jean-Michel Marin
Compstat: Proceedings in Computational Statistics : 18th Symposium Held in Porto, Portugal 2008, pp.337-348
01/01/2008

Résumé

Business & Economics Economics Mathematics Physical Sciences Science & Technology Social Sciences Statistics & Probability
Model selection is a difficult task for which it is often profitable to take into account the modeller point of view. Hidden structure models are a, good example for which this point of view call be dealt with in a simple way. In the model-based clustering context, we present model selection criteria focussing oil the clustering purpose. Their rationale and theoretical features are given and their practical behavior in comparison with classical penalized likelihood criteria is discussed from numerical experiments.

Indicateurs

1 Consultations de la notice

Détails

Logo image