Confidence Intervals for Adaptive Regression Estimation on the Besov Spaces - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1999

Confidence Intervals for Adaptive Regression Estimation on the Besov Spaces

Abstract

The problem of adaptive estimation of the regression function f from noisy observations is concerned. A confidence interval for the L_2-error for wavelet adaptive estimator is provided. We show that if f belongs to a Besov class, the proposed confidence interval is minimax.
Fichier principal
Vignette du fichier
RR-3643.pdf (339.2 Ko) Télécharger le fichier

Dates and versions

inria-00073030 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00073030 , version 1

Cite

Anatoli B. Juditsky, Sophie Lambert-Lacroix. Confidence Intervals for Adaptive Regression Estimation on the Besov Spaces. [Research Report] RR-3643, INRIA. 1999. ⟨inria-00073030⟩
51 View
116 Download

Share

Gmail Facebook Twitter LinkedIn More