Title :

Segmentation in the mean of heteroscedastic data via resampling or cross-validation

Author(s) :

Celisse, Alain [Auteur]
Mathématiques et Informatique Appliquées [MIA-Paris]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Université de Lille, Sciences et Technologies
Arlot, Sylvain [Auteur]
Laboratoire d'informatique de l'école normale supérieure [LIENS]
École normale supérieure - Cachan [ENS Cachan]

Conference title :

Workshop Change-Point Detection Methods and Applications

City :

Paris

Country :

France

Start date of the conference :

2008-09-11

Publication date :

2010

Keyword(s) :

hétéroscédastique
point de modification

English keyword(s) :

change-point detection
resampling
cross-validation
model selection
heteroscedastic data
cgh profile segmentation

HAL domain(s) :

Mathématiques [math]
Informatique [cs]

English abstract : [en]

This paper tackles the problem of detecting abrupt changes in the mean of a heteroscedastic signal by model selection, without knowledge on the variations of the noise. A new family of change-point detection procedures is ...
Show more >This paper tackles the problem of detecting abrupt changes in the mean of a heteroscedastic signal by model selection, without knowledge on the variations of the noise. A new family of change-point detection procedures is proposed, showing that cross-validation methods can be successful in the heteroscedastic framework, whereas most existing procedures are not robust to heteroscedasticity. The robustness to heteroscedasticity of the proposed procedures is supported by an extensive simulation study, together with recent partial theoretical results. An application to Comparative Genomic Hybridization (CGH) data is provided, showing that robustness to heteroscedasticity can indeed be required for their analysis.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Nationale

Popular science :

Non

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL