Density deconvolution based on wavelets with bounded supports

Under the assumption that both convolution densities, g and q, have finite degrees of smoothness, we construct a nonlinear wavelet estimator of the unknown density g based on wavelets with bounded supports. We show that this estimator provides local adaptivity to the unknown smoothness of g and, hence, performs better than the estimator based on Meyer-type wavelets if g has irregular behavior.

MoreLess

Year of publication:	2002
Authors:	Pensky, Marianna
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 56.2002, 3, p. 261-269
Publisher:	Elsevier
Subject:	Deconvolution Wavelet Thresholding

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005137851