Please use this identifier to cite or link to this item:
Title: Comparison of Mixture and Classification Maximum Likelihood Approaches in Poisson Regression Models
Authors: Faria, Susana
Soromenho, Gilda
Keywords: Simulation study
EM algorithm
Mixture Poisson Regression Models
Classification EM algorithm
Issue Date: Aug-2008
Citation: Compstat 2008-Proceedings in Computational Statistics, Vol. 2
Abstract: In this work, we propose to compare two algorithms to compute maximum likelihood estimators of the parameters of a mixture Poisson regression models. To estimate these parameters, we may use the EM algorithm in a mixture approach or the CEM algorithm in a classification approach. The comparison of the two procedures was done through a simulation study of the performance of these approaches on simulated data sets in a target number of iterations. Simulation results show that the CEM algorithm is a good alternative to the EM algorithm for fitting Poisson mixture regression models, having the advantage of converging more quickly.
Peer review: yes
Appears in Collections:FPCE - Comunicações

Files in This Item:
File Description SizeFormat 
artigo15-01.pdf207 kBAdobe PDFView/Open

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

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