Please use this identifier to cite or link to this item: http://hdl.handle.net/10773/15003
Title: Regularization with maximum entropy and quantum electrodynamics: the MERG(E) estimators
Author: Macedo, Pedro
Scotto, Manuel
Silva, Elvira
Keywords: Collinearity
Linear regression
Maximum entropy
Micronumerosity
Outliers
Quantum electrodynamics
Issue Date: 2016
Publisher: Taylor & Francis
Abstract: It is well-known that under fairly conditions linear regression becomes a powerful statistical tool. In practice, however, some of these conditions are usually not satisfied and regression models become ill-posed, implying that the application of traditional estimation methods may lead to non-unique or highly unstable solutions. Addressing this issue, in this paper a new class of maximum entropy estimators suitable for dealing with ill-posed models, namely for the estimation of regression models with small samples sizes affected by collinearity and outliers, is introduced. The performance of the new estimators is illustrated through several simulation studies.
Peer review: yes
URI: http://hdl.handle.net/10773/15003
DOI: 10.1080/03610918.2014.957838
ISSN: 0361-0918
Appears in Collections:CIDMA - Artigos

Files in This Item:
File Description SizeFormat 
PaperCIS-SC2016.pdfPaper in CIS-SC 2016366.01 kBAdobe PDFView/Open


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.