Let Y be a mixed stationary Poisson hyperplane tessellation with finite intensity in the d-dimensional Euclidean space and Y′ a stationary Poisson hyperplane tessellation with the same intensity and directional distribution as Y. Denote by D0, D0′ the cells of Y, Y′ respectively containing a fixed point x0 and by V(D0), V(D0′) their volumes.

It is well-known that Poisson lines in the plane, with orientation distribution Θ on [0, π), generate a (random) tessellation M0 of (random) convex polygons whose characteristics (area, perimeter, etc.) conform, in an ergodic sense, to a certain class {DΘ} of distributions.

Parameter estimation for a two-dimensional point pattern is difficult because most of the available stochastic models have intractable likelihoods ([2]). An exception is the class of Gibbs or Markov point processes ([1], [5]), where the likelihood typically forms an exponential family and is given explicitly up to a normalising constant. However, the latter is not known analytically, so parameter estimates must be based on approximations ([3], [6], [7]). In this paper we present comparisons amongst the different techniques available in the literature to obtain an approximation of the maximum likelihood estimate (MLE). Two stochastic methods are specifically illustrated: a Newton-Raphson algorithm ([7]) and the Robbins-Monro procedure ([8]). We use a very simple point process model, the Strauss process ([4]), to test and compare those approximations.

For a discrete random set defined on a bounded subset B ⊂ ℤ2, the paper proposes a test for checking the Boolean hypothesis against its natural alternatives: models whose process of germs show a major tendency versus regularity or aggregation represented by a hardcore process or Poisson's cluster process. The test is based on the contents, T, of the difference XD - X, where X is the original model and XD = X ⊕ C is its dilation by the structurant element C.

A new class of Gibbsian models with potentials associated with the connected components or homogeneous parts of images is introduced. The relationship with Markov random fields and marked point processes is explored and spatial Markov properties are established. Further, extensions to infinite lattices are studied. Statistical inference problems including geostatistical applications and statistical image analysis are also discussed. Finally, simulation studies are presented which show that the models may be appropriate for a variety of interesting patterns.

Families of Poisson processes defined on general state spaces and with the intensity measure scaled by a positive parameter are investigated. In particular, mean value relations with respect to the scale parameter are established and used to derive various Gamma-type results for certain geometrical characteristics determined by finite subprocesses. In particular, we deduce Miles' complementary theorem. Applications of the results within stochastic geometry and particularly for random tesselations are discussed.

Consider homogeneous spatial particle systems consisting of homothetic particles. Important examples are systems of balls or systems of homothetic convex polyhedrons. For such models the distribution of the typical particle can be expressed by the distribution of one size parameter. We are interested in the stereological estimation of this size parameter distribution from observations on two-dimensional section planes.

Let X, Y be two sets of positive reach in ℝd. The translative integral formula says that, for 0 ≦ k ≦ d − 1 and bounded Borel subsets A, B ε ℝd, where is the curvature measure (of order k) of X and is the mixed curvature measure of the sets X, Y and order r, S [1]. The mixed curvature measures are introduced by means of rectifiable currents, which leads to a relatively simple proof of (1). The proof needs an additional assumption on X, Y assuring that also reach (X ∩ Yz) > 0 for almost all z. This assumption is satisfied automatically for convex bodies, in dimension 2, or for sets with a sufficiently smooth boundary. Using the additivity of mixed curvature measures, (1) can be extended to unions of sets of positive reach.

The chorioallantoic membrane (CAM) of chick eggs is a well-studied embryonic organ, where the growth of blood vessels can be easily inspected in the living state, and in a quasi-two-dimensional tissue sheet. Structural and physiological knowledge about this organ was combined to define a stochastic growth process (Sandau and Kurz 1994).

The starting point for this work was the following astonishing observation regarding stationary line processes in the plane.

We consider two mechanisms for simulating spatial patterns of hard-core non-spherical particles, namely the random sequential packing (RSP) and the Markov chain Monte Carlo (MCMC) procedures. The former is described as follows: we put a particle one-by-one into a finite region by sampling its location x and direction θ uniformly at random; if it does not overlap with other particles put before, it is put successfully, otherwise, we discard it and try another uniform sampling of (x, θ); by repeating the above, we can obtain a set of non-overlapping particles. The MCMC procedure is the following: we first give a certain non-overlapping pattern of non-spherical particles prepared in a random or a regular manner; then we select a particle and sample its new trial location x and direction θ at random; if the new sample (x, θ) is accepted, i.e. it does not overlap with other particles, the selected particle is moved to the new ‘position’, otherwise the particle is retained at the old position; by repeating the above, a series of a set of non-overlapping particles is generated.

Siegel (1993) presented a covariance identity involving normal variables that seems to flout notions of dependence. We show that it has an explanation from an unexpected quarter: convex geometry and the centroid known as the Steiner point. In the same geometric spirit, we introduce another identity for Gaussian covariances based on an Euler identity for the Steiner point.

The study of spatial distributions which arise from independent multiplicative cascades can be traced back at least to the efforts by the Russian school led by Andrei N. Kolmogorov on the statistical theory of turbulence. However, largely owing to the intriguing statistical/geometric scaling properties so heavily emphasized by Benoit Mandelbrot, and to the rich mathematical foundations begun by Jean-Pierre Kahane and Jacques Peyriere in the middle 1970's and continuing to the present, there has been a growing interest in random cascades both in the physical sciences and in mathematics. Our objective is to review some of the principal aspects of the theory and applications of independent cascades as well as some recent extensions.

Let dimH, E be the Hausdorff dimension and dimP, E the packing dimension of the subset E of ℝn given by the unique exponent where the corresponding Hausdorff or packing measure of E jumps from infinity to zero.

We show that a Poisson cluster point process is a nearest-neighbour Markov point process [2] if the clusters have uniformly bounded diameter. It is typically not a finite-range Markov point process in the sense of Ripley and Kelly [12]. Furthermore, when the parent Poisson process is replaced by a Markov or nearest-neighbour Markov point process, the resulting cluster process is also nearest-neighbour Markov, provided all clusters are non-empty. In particular, the nearest-neighbour Markov property is preserved when points of the process are independently randomly translated, but not when they are randomly thinned.

Is the intersection between an arbitrary but fixed plane and the spatial Poisson Voronoi tessellation a planar Voronoi tessellation? In this paper a negative answer is given to this long-standing question in stochastic geometry. The answer remains negative for the intersection between a t-dimensional linear affine space and the d-dimensional Poisson Voronoi tesssellation, where 2 ≦ t ≦ d − 1. Moreover, it is shown that each cell on this intersection is almost surely a non-Voronoi cell.

A planar graph contains faces which can be classified into types depending on the number of edges on the face boundaries. Under various natural rules for randomly dividing faces by the addition of new edges, we investigate the limiting distribution of face type as the number of divisions increases.

The Hausdorff distance between a compact convex set K ⊂ ℝd and random sets is studied. Basic inequalities are derived for the case of being a convex subset of K. If applied to special sequences of such random sets, these inequalities yield rates of almost sure convergence. With the help of duality considerations these results are extended to the case of being the intersection of a random family of halfspaces containing K.

Methods of estimation of the oriented direction distribution (i.e. the distribution of unit outer normals over the boundary) of a planar set from the convex ring are proposed. The methods are based on an estimation of the area dilation of the investigated set by chosen test sets.

Markov chain processes are becoming increasingly popular as a means of modelling various phenomena in different disciplines. For example, a new approach to the investigation of the electrical activity of molecular structures known as ion channels is to analyse raw digitized current recordings using Markov chain models. An outstanding question which arises with the application of such models is how to determine the number of states required for the Markov chain to characterize the observed process. In this paper we derive a realization theorem showing that observations on a finite state Markov chain embedded in continuous noise can be synthesized as values obtained from an autoregressive moving-average data generating mechanism. We then use this realization result to motivate the construction of a procedure for identifying the state dimension of the hidden Markov chain. The identification technique is based on a new approach to the estimation of the order of an autoregressive moving-average process. Conditions for the method to produce strongly consistent estimates of the state dimension are given. The asymptotic distribution of the statistic underlying the identification process is also presented and shown to yield critical values commensurate with the requirements for strong consistency.