A Bayesian MCMC method for point process models with intractable normalising constants

Kasper Klitgaard Berthelsen, Jesper Møller

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskning

Abstrakt

We present new methodology for drawing samples from a posterior distribution when the likelihood function is only specified up to a normalising constant. Our method is "on-line" as compared with alternative approaches to the problem which require "off-line" computations. Since it is needed to simulate from the "unknown distribution", perfect simulation algorithms become useful. We illustrate the method in cases whre the likelihood is given by a Markov point process model. Particularly, we consider semi-parametric Bayesian inference in connection to both inhomogeneous Markov point process models and pairwise interaction point processes.
OriginalsprogEngelsk
TitelProceedings from the International Conference on Spatial Point Process Modelling and Its Applications
RedaktørerBaddeley, Gregori, Mateu, Stoica, Stoyan
ForlagPublicacions de la Universitat Jaume I
Publikationsdato2004
Sider7-15
ISBN (Trykt)8480214759
StatusUdgivet - 2004
BegivenhedInternational Conference on Spatial Point Process Modelling and Its Applications -
Varighed: 19 maj 2010 → …

Konference

KonferenceInternational Conference on Spatial Point Process Modelling and Its Applications
Periode19/05/2010 → …

Bibliografisk note

ISSN ; -

Fingeraftryk Dyk ned i forskningsemnerne om 'A Bayesian MCMC method for point process models with intractable normalising constants'. Sammen danner de et unikt fingeraftryk.

Citationsformater