The Candy model: properties and inference
- 28 May 2003
- journal article
- Published by Wiley in Statistica Neerlandica
- Vol. 57 (2) , 177-206
- https://doi.org/10.1111/1467-9574.00227
Abstract
In this paper we study the Candy model, a marked point process introduced byStoicaet al. (2000). We prove Ruelle and local stability, investigate its Markov properties, and discuss how the model may be sampled. Finally, we consider estimation of the model parameters and present a simulation study.Keywords
This publication has 27 references indexed in Scilit:
- Maximum Likelihood Estimation for Spatial Models by Markov Chain Monte Carlo Stochastic ApproximationJournal of the Royal Statistical Society Series B: Statistical Methodology, 2001
- Perfect simulation using dominating processes on ordered spaces, with application to locally stable point processesAdvances in Applied Probability, 2000
- Bayesian object identificationBiometrika, 1999
- Estimation of Markov random field prior parameters using Markov chain Monte Carlo maximum likelihoodIEEE Transactions on Image Processing, 1999
- Convergence of a stochastic approximation version of the EM algorithmThe Annals of Statistics, 1999
- Bayesian object recognition with baddeley's delta lossAdvances in Applied Probability, 1998
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determinationBiometrika, 1995
- Markov Point ProcessesJournal of the London Mathematical Society, 1977
- Optimum Monte-Carlo sampling using Markov chainsBiometrika, 1973
- Monte Carlo Calculations of the Radial Distribution Functions for a Proton?Electron PlasmaAustralian Journal of Physics, 1965