Quermass-interaction processes: conditions for stability
Let \(S\) be \(\mathbb R^d\) or a compact subset, \(\mu\) be a finite diffuse measure on \(S\) and \(\nu\) be a probability measure on \(C(\mathbb K)\) (where \(C(\mathbb K)\) is the set of all ovoids, that is the set of all non-empty convex compact sets with non-empty interior). The authors define new germ-grain models by their density with respect to a Poisson marked point process of intensity \(\mu\otimes \nu\) on \(S\times C(\mathbb K)\). Realizations are denoted by \(\mathbf y = \{(x_1, K_1), \dots, (x_n, K_n)\}\). A quermass-interaction germ-grain model is absolutely continuous with respect to a Poisson marked point process on \(S\times C(\mathbb K)\) with intensity \(\mu\otimes \nu\) and has density given by \(p(\mathbf y) = \alpha \beta^{n(y)} \exp[ - \sum_{j=0}^d \gamma_j W_j^d(\mathbb U_{\mathbf y})].\) Here \(\beta> 0\) and \(\gamma_j\in R\) are model parameters, \(W_j^d\) is the additive extension of \(j\)th Minkovski functional on the convex ring \(\mathbb R\), and \(\mathbb U_{\mathbf y}\) is the set union \(\bigcup_{i=1}^n (K_i+ x_i)\). If only the area functional is used, then the area-interaction point process is recovered [see \textit{A. J. Baddeley} and \textit{M. N. M. van Lieshout}, Ann. Inst. Stat. Math. 47, No. 4, 601-619 (1995; Zbl 0848.60051)]. New point processes arise if we include the perimeter length functional, or the Euler-Poincaré characteristic (number of components minus number of holes). The main question addressed by the paper is to establish conditions under which planar quermass-interaction processes are stable in the sense of Ruelle. This is important because stability is an accessible condition for the density to be proper. The paper is divided into seven sections: \S 1 covers preliminaries on stochastic geometry; \S 2 defines quermass-interaction germ-grain models and random sets; \S 3 considers the range of permissible parameter values (\(\gamma_j\), \(j=0, \dots{}, d\)) under which the Euler-Poincaré characteristic yields a stable germ-grain process; \S 4 shows stability when grains are planar disks; \S 5 considers the case when grains are convex polygons, in which case a lower bound on interior angles and side-lengths is needed; \S 6 indicates future investigations of these point processes.
- Mixture formulae for shot noise weighted point processes
- Spatio-temporal model for a random set given by a union of interacting discs
- Asymptotic properties of the maximum pseudo-likelihood estimator for stationary Gibbs point processes including the Lennard-Jones model
- Marked Gibbs point processes with unbounded interaction: an existence result
- Assessing similarity of random sets via skeletons
- Testing equality of distributions of random convex compact sets via theory of \(\mathfrak{N} \)-distances
- Disagreement percolation for Gibbs ball models
- Interaction processes for unions of facets, the asymptotic behaviour with increasing intensity
- Interacting neighbour point processes: Some models for clustering
- Takacs-Fiksel method for stationary marked Gibbs point processes
- Estimation of the intensity parameter of the germ-grain quermass-interaction model when the number of germs is not observed
- Likelihood Inference for Unions of Interacting Discs
- Quermass-interaction process with convex compact grains.
- Power diagrams and interaction processes for unions of discs
- The existence of quermass-interaction processes for nonlocally stable interaction and nonbounded convex grains
- Dimension reduction in extended quermass-interaction process
- On the use of particle Markov chain Monte Carlo in parameter estimation of space-time interacting discs
- Approaches to asymptotics for \(U\)-statistics of Gibbs facet processes
- Fractal and stochastic geometry inference for breast cancer: a case study with random fractal models and quermass-interaction process
- Topological data analysis for random sets and its application in detecting outliers and goodness of fit testing
- Liquid-gas phase transition for Gibbs point process with Quermass interaction
- Discussion of ``Marked spatial point processes: current state and extensions to point processes on linear networks
- Existence of Gibbsian point processes with geometry-dependent interactions
- \(R\)-local Delaunay inhibition model
This page was built for publication: Quermass-interaction processes: conditions for stability
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4705779)
