Moment Priors for Bayesian Model Choice with Applications to Directed Acyclic Graphs

Guido Consonni Author_Email: guido.consonni@unipv.it and Luca La Rocca Author_Email:luca.larocca@unimore.it
Additional contact information
Guido Consonni Author_Email: guido.consonni@unipv.it: Department of Economics and Quantitative Methods, University of Pavia
Luca La Rocca Author_Email:luca.larocca@unimore.it: Dipartimento di Comunicazione e Economia, University of Modena and Reggio Emilia

No 115, Quaderni di Dipartimento from University of Pavia, Department of Economics and Quantitative Methods

Abstract: We propose a new method for the objective comparison of two nested models based on non-local priors. More specifically, starting with a default prior under each of the two models, we construct a moment prior under the larger model, and then use the fractional Bayes factor for a comparison. Non-local priors have been recently introduced to obtain a better separation between nested models, thus accelerating the learning behaviour, relative to currently used local priors, when the smaller model holds. Although the argument showing the superior performance of non-local priors is asymptotic, the improvement they produce is already apparent for small to moderate samples sizes, which makes them a useful and practical tool. As a by-product, it turns out that routinely used objective methods, such as ordinary fractional Bayes factors, are alarmingly slow in learning that the smaller model holds. On the downside, when the larger model holds, non-local priors exhibit a weaker discriminatory power against sampling distributions close to the smaller model. However, this drawback becomes rapidly negligible as the sample size grows, because the learning rate of the Bayes factor under the larger model is exponentially fast, whether one uses local or non-local priors. We apply our methodology to directed acyclic graph models having a Gaussian distribution. Because of the recursive nature of the joint density, and the assumption of global parameter independence embodied in our prior, calculations need only be performed for individual vertices admitting a distinct parent structure under the two graphs; additionally we obtain closed-form expressions as in the ordinary conjugate case. We provide illustrations of our method for a simple three-variable case, as well as for a more elaborate seven-variable situation. Although we concentrate on pairwise comparisons of nested models, our procedure can be implemented to carry-out a search over the space of all models.

Keywords: Fractional Bayes factor; Gaussian graphical model; Non-local prior; Objective Bayes network; Stochastic search; Structural learning. (search for similar items in EconPapers)
Pages: 19 pages
Date: 2010-06
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://dem-web.unipv.it/web/docs/dipeco/quad/ps/RePEc/pav/wpaper/q115.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:pav:wpaper:115

Access Statistics for this paper

More papers in Quaderni di Dipartimento from University of Pavia, Department of Economics and Quantitative Methods Contact information at EDIRC.
Bibliographic data for series maintained by Paolo Bonomolo ( this e-mail address is bad, please contact ).