Statistics and Computing

, Volume 27, Issue 5, pp 1383–1399

Multiscale local polynomial decompositions using bandwidths as scales

Article

DOI: 10.1007/s11222-016-9692-8

Cite this article as:
Jansen, M. & Amghar, M. Stat Comput (2017) 27: 1383. doi:10.1007/s11222-016-9692-8
  • 234 Downloads

Abstract

The multiscale local polynomial transform, developped in this paper, combines the benefits from local polynomial smoothing with sparse multiscale decompositions. The contribution of the paper is twofold. First, it focusses on the bandwidths used throughout the transform. These bandwidths operate as user controlled scales in a multiscale analysis, which is explained to be of particular interest in the case of nonequispaced data. The paper presents both a likelihood based optimal bandwidth selection and a fast, heuristic approach. The second contribution of the paper is the combination of local polynomial smoothing with orthogonal prefilters, similar to Daubechies’ wavelet filters, but defined on irregularly spaced covariate values.

Keywords

Local polynomial Wavelet Multiscale Sparsity 

Funding information

Funder NameGrant NumberFunding Note
IAP, Belgian Government
  • P7/06

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Department of MathematicsUniversité libre de BruxellesBrusselsBelgium

Personalised recommendations