Testing convex hypotheses on the mean of a Gaussian vector. Application to testing qualitative hypotheses on a regression function - Laboratoire Jean-Alexandre Dieudonné Accéder directement au contenu
Article Dans Une Revue Annals of Statistics Année : 2005

Testing convex hypotheses on the mean of a Gaussian vector. Application to testing qualitative hypotheses on a regression function

Résumé

In this paper we propose a general methodology, based on multiple testing, for testing that the mean of a Gaussian vector in ℝn belongs to a convex set. We show that the test achieves its nominal level, and characterize a class of vectors over which the tests achieve a prescribed power. In the functional regression model this general methodology is applied to test some qualitative hypotheses on the regression function. For example, we test that the regression function is positive, increasing, convex, or more generally, satisfies a differential inequality. Uniform separation rates over classes of smooth functions are established and a comparison with other results in the literature is provided. A simulation study evaluates some of the procedures for testing monotonicity.
Fichier non déposé

Dates et versions

hal-00756077 , version 1 (22-11-2012)

Identifiants

  • HAL Id : hal-00756077 , version 1
  • PRODINRA : 244191
  • WOS : 000228576800013

Citer

Yannick Baraud, Sylvie Huet, Béatrice Laurent. Testing convex hypotheses on the mean of a Gaussian vector. Application to testing qualitative hypotheses on a regression function. Annals of Statistics, 2005, 33 (1), pp.214-257. ⟨hal-00756077⟩
129 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More