Title: A discussion on Bayesian analysis : Selecting Noninformative Priors
Abstract: In this note, following the publication of Seaman III, Seaman Jr and Stamey(2012) we re ect on an aspect of Bayesian statistics, namely the selection of a priordensity on the parameters. In some cases Bayesian data analysis remains stable underdi erent noninformative choices of prior distributions. As discussed in [18], there maybe unintended consequences on the posterior distribution for some functions of interestof the choice of a noninformative prior and according to the authors, this is a problemthat \is often ignored in applications of Bayesian inference (p.77). The authors focusedon four examples and analyzed each of them for several particular choices of prior. Here,we consider a new these examples and discuss the Bayesian processing of their modelsassuming di erent prior choices while the results are based on xed data sets. Theconclusion of our research leads us to infer a stability of the posterior distributions ofthe parameters and to state that the e ect of the noninformative prior is essentiallynegligible.
Publication Year: 2014
Publication Date: 2014-02-25
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot