Please use this identifier to cite or link to this item:
Type: Artigo de evento
Title: Bayesian Modeling Of Censored Partial Linear Models Using Scale-mixtures Of Normal Distributions
Author: Castro L.M.
Lachos V.H.
Ferreira G.P.
Arellano-valle R.B.
Abstract: Regression models where the dependent variable is censored (limited) are usually considered in statistical analysis. Particularly, the case of a truncation to the left of zero and a normality assumption for the error terms is studied in detail by [1] in the well known Tobit model. In the present article, this typical censored regression model is extended by considering a partial linear model with errors belonging to the class of scale mixture of normal distributions. We achieve a fully Bayesian inference by adopting a Metropolis algorithm within a Gibbs sampler. The likelihood function isutilized to compute not only some Bayesian model selection measures but also to develop Bayesian case-deletion influencediagnostics based on the q-divergence measures. We evaluate the performances of the proposed methods with simulated data. In addition, we present an application in order to know what type of variables affect the income of housewives. © 2012 American Institute of Physics.
Rights: aberto
Identifier DOI: 10.1063/1.4759591
Date Issue: 2012
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
There are no files associated with this item.

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