Chapter 3 in Böcker, (ed.) (2010). Rethinking Risk Measurement and Reporting: Uncertainty, Bayesian Analysis and Expert Judgement Risk Books ISBN-10: 1-906348-40-5, ISBN-13: 978-1-906348-40-3, pp. 69-106.
Ioannis Ntzoufras
Publications Page
Ioannis Ntzoufras
Department of Statistics,
Athens University of Economics and Business,
Athens, GREECE;
e-mail: ntzoufras@aueb.gr
Chapter 3 in Böcker, (ed.) (2010). Rethinking Risk Measurement and Reporting: Uncertainty, Bayesian Analysis and Expert Judgement Risk Books ISBN-10: 1-906348-40-5, ISBN-13: 978-1-906348-40-3, pp. 69-106.
SYNOPSIS
In this chapter, we implement Bayesian methods in regression models which are an essential tool in modern statistical science. They can be used for both interpretation of social or economic phenomena and prediction of future outcomes which is of major interest in risk analysis. Possible prior specifications are described in detail. Posterior inference is illustrated focusing on the conjugate case. Bayesian variable selection methods for the conjugate case are also illustrated while more advanced topics such as variable selection using MCMC and evaluation of the structural assumptions is briefly discussed accompanied with references for further reading. The chapter closes with a short discussion and conclusion.
Download:
R code for illustrated example [Corrected 12/6/2014].
Corrected results for empirical prior [12/6/2014].
All
Contents Copyright.