High-dimensional test for normality
Type de document :
Communication dans un congrès avec actes
URL permanente :
Titre :
High-dimensional test for normality
Auteur(s) :
Titre de la manifestation scientifique :
Journées des Statistiques
Ville :
Rennes
Pays :
France
Date de début de la manifestation scientifique :
2014-06-02
Date de publication :
2014-06-02
Discipline(s) HAL :
Mathématiques [math]/Statistiques [math.ST]
Résumé en anglais : [en]
A new goodness-of-fit test for normality in high-dimension (and Reproducing Kernel Hilbert Space) is proposed. It shares common ideas with the Maximum Mean Discrepancy (MMD) it outperforms both in terms of computation time ...
Lire la suite >A new goodness-of-fit test for normality in high-dimension (and Reproducing Kernel Hilbert Space) is proposed. It shares common ideas with the Maximum Mean Discrepancy (MMD) it outperforms both in terms of computation time and applicability to a wider range of data. Theoretical results are derived for the Type-I and Type-II errors. They guarantee the control of Type-I error at prescribed level and an exponentially fast decrease of the Type-II error. Synthetic and real data also illustrate the practical improvement allowed by our test compared with other leading approaches in high-dimensional settings.Lire moins >
Lire la suite >A new goodness-of-fit test for normality in high-dimension (and Reproducing Kernel Hilbert Space) is proposed. It shares common ideas with the Maximum Mean Discrepancy (MMD) it outperforms both in terms of computation time and applicability to a wider range of data. Theoretical results are derived for the Type-I and Type-II errors. They guarantee the control of Type-I error at prescribed level and an exponentially fast decrease of the Type-II error. Synthetic and real data also illustrate the practical improvement allowed by our test compared with other leading approaches in high-dimensional settings.Lire moins >
Langue :
Anglais
Audience :
Nationale
Vulgarisation :
Non
Établissement(s) :
CNRS
Université de Lille
Université de Lille
Date de dépôt :
2020-06-08T14:10:37Z