PARAMETER-ESTIMATION FOR MARKED GIBBS POINT-PROCESSES THROUGH THE MAXIMUM PSEUDO-LIKELIHOOD METHOD

Authors
GOULARD M SARKKA A GRABARNIK P
Citation
M. Goulard et al., PARAMETER-ESTIMATION FOR MARKED GIBBS POINT-PROCESSES THROUGH THE MAXIMUM PSEUDO-LIKELIHOOD METHOD, Scandinavian journal of statistics, 23(3), 1996, pp. 365-379
Citations number
26
Categorie Soggetti
Statistic & Probability","Statistic & Probability
Journal title
Scandinavian journal of statistics → ACNP
ISSN journal
03036898
Volume
23
Issue
3
Year of publication
1996
Pages
365 - 379
Database
ISI
SICI code
0303-6898(1996)23:3<365:PFMGPT>2.0.ZU;2-B
Abstract
A general definition and derivation of the pseudo-likelihood function for marked Gibbs point processes are given. The maximum pseudo-likelih ood method is illustrated by fitting some marked models to two data se ts. In addition, a simulation study of statistical properties of the e stimators is presented.