Statistics Papers

Document Type

Working Paper

Date of this Version

4-15-1999

Publication Source

Statistics & Probability Letters

Volume

42

Issue

3

Start Page

313

Last Page

321

DOI

10.1016/S0167-7152(98)00223-5

Abstract

We show that for nonparametric regression if the samples have random uniform design, the wavelet method with universal thresholding can be applied directly to the samples as if they were equispaced. The resulting estimator achieves within a logarithmic factor from the minimax rate of convergence over a family of Hölder classes. Simulation result is also discussed.

Copyright/Permission Statement

© 1999. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.

Keywords

wavelets, nonparametric regression, minimax, adaptivity, Hölder class

Share

COinS
 

Date Posted: 27 November 2017

This document has been peer reviewed.