Robust scale estimation for the generalized gaussian probability density function

Rozenn Dahyot (Author), Simon Wilson (Author)

Abstract

This article proposes a robust way to estimate the scale parameter of a generalised centered Gaussian mixture. The principle relies on the associationof samples of this mixture to generate samples of a new variable that shows relevant distribution properties to estimate the unknown parameter.In fact, the distribution of this new variable shows a maximum that is linked to this scale parameter. Using nonparametric modelling of the distribution and the MeanShift procedure, the relevant peak is identified and an estimate is computed. The whole procedure is fully automatic and does not require any prior settings. It is applied to regression problems, and digital data processing.

Keywords

No keyword data available

Data

Language:	English
Year of publishing:	2006
Typology:	1.01 - Original Scientific Article
Organization:	UL FDV - Faculty of Social Sciences
Publisher:	Fakulteta za družbene vede
UDC:	303
COBISS:	25330013
ISSN:	1854-0023
Views:	302
Downloads:	54
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Unknown
Secondary keywords:	Merske lestvice;Metric scales;
URN:	URN:NBN:SI
Type (COBISS):	Not categorized
Pages:	str. 21-37
Volume:	ǂVol. ǂ3
Issue:	ǂno. ǂ1
Chronology:	2006
Keywords (UDC):	social sciences;družbene vede;methods of the social sciences;metode družbenih ved;
ID:	40633