A note on conflict of information and subexponential densities

The Bayesian approach allows for uncertainty about both the model and the prior settings. Such uncertainty can only be stated by probability distributions. The adoption of robust distributions deals with potential conflict of information between the prior and the data. In this paper, we present sufficient conditions for a conflict to be solved in favour of either source of information in terms of subexponential densities.

MoreLess

Year of publication:	2012
Authors:	Rifo, L.R. ; Santos, J.D.
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 82.2012, 4, p. 840-842
Publisher:	Elsevier
Subject:	Bayesian inference \| Conflict of information \| Subexponential density \| Heavy-tailed distribution

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010571767