Block thresholding for a density estimation problem with a change-point

Christophe Chesneau (1)

1 LMNO - Laboratoire de Mathématiques Nicolas Oresme

We consider a density estimation problem with a change-point. We develop an adaptive wavelet estimator constructed from a block thresholding rule. Adopting the minimax point of view under the Lp risk (with p>1) over Besov balls, we prove that it is near optimal.

Mots clés: Density estimation; wavelets; block thresholding

Domaines: Statistiques [math.ST]

Christophe Chesneau. Block thresholding for a density estimation problem with a change-point. 2008. ⟨hal-00268393⟩