HAL: hal-00408696, version 2

arXiv: 0908.0128

Detailed view

Export this paper BibTeX - EndNote - TEI - RefWorks -

Available versions:

v1 (2009-08-02)

v2 (2009-10-15)

v3 (2011-02-28)

Multiplicative Bias Corrected Nonparametric Smoothers

Nicolas Hengartner 1, Eric Matzner-Løber 2, 3, Laurent Rouvière (  Corresponding author ) 2, 4, Thomas Burr 1

(2009-10-15)

The paper presents a multiplicative bias reduction estimator for nonparametric regression. The approach consists to apply a multiplicative bias correction to an oversmooth pilot estimator. In Burr et al. [2010], this method has been tested to estimate energy spectra. For such data set, it was observed that the method allows to decrease bias with negligible increase in variance. In this paper, we study the asymptotic properties of the resulting estimate and prove that this estimate has zero asymptotic bias and the same asymptotic variance as the local linear estimate. Simulations show that our asymptotic results are available for modest sample sizes.

1:	Theorical Division (LANL)
	Los Alamos National Laboratory,
2:	Institut de Recherche Mathématique de Rennes (IRMAR)
	CNRS : UMR6625 – Université de Rennes 1 – École normale supérieure de Cachan - ENS Cachan – Institut National des Sciences Appliquées (INSA) : - RENNES – Université de Rennes II - Haute Bretagne
3:	Université de Haute Bretagne - Rennes 2 (UHB)
	Université de Rennes II - Haute Bretagne
4:	Centre de Recherche en Économie et Statistique (CREST)
	INSEE – École Nationale de la Statistique et de l'Administration Économique

Subject

:

Mathematics/Statistics Statistics/Statistics Theory

Keyword(s): Nonparametric regression – bias reduction – local linear estimate

hal-00408696, version 2

http://hal.archives-ouvertes.fr/hal-00408696

oai:hal.archives-ouvertes.fr:hal-00408696

From: Laurent Rouvière <>

Submitted on: Thursday, 15 October 2009 18:37:59

Updated on: Monday, 28 February 2011 17:27:31