liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Non-parametric Bayesian inference for integrals with respect to an unknown finite measure
Linköping University, The Institute of Technology. Linköping University, Department of Mathematics, Mathematical Statistics .
2008 (English)In: Scandinavian Journal of Statistics, ISSN 0303-6898, Vol. 35, no 2, 369-384 p.Article in journal (Refereed) Published
Abstract [en]

We consider the problem of estimating a collection of integrals with respect to an unknown finite measure μ from noisy observations of some of the integrals. A new method to carry out Bayesian inference for the integrals is proposed. We use a Dirichlet or Gamma process as a prior for μ, and construct an approximation to the posterior distribution of the integrals using the sampling importance resampling algorithm and samples from a new multidimensional version of a Markov chain by Feigin and Tweedie. We prove that the Markov chain is positive Harris recurrent, and that the approximating distribution converges weakly to the posterior as the sample size increases, under a mild integrability condition. Applications to polymer chemistry and mathematical finance are given. © 2008 Board of the Foundation of the Scandinavian Journal of Statistics.

Place, publisher, year, edition, pages
2008. Vol. 35, no 2, 369-384 p.
National Category
URN: urn:nbn:se:liu:diva-43920DOI: 10.1111/j.1467-9469.2007.00579.xLocal ID: 75119OAI: diva2:264781
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2011-01-10

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Erhardsson, Torkel
By organisation
The Institute of TechnologyMathematical Statistics
In the same journal
Scandinavian Journal of Statistics

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 354 hits
ReferencesLink to record
Permanent link

Direct link