Stochastic order for alpha-permanental point processes

We establish relations of stochastic comparison among point processes elements of the set of alpha-permanental point processes. This set contains in particular, the determinantal point processes, the Poisson point processes and the permanental point processes. We show that these three classes of point processes can be ordered according to the increasing stochastic order. Elementary particles provide illustrations of some of the obtained relations of stochastic comparison.     

Thinning of point processes,revisited

ＴＨＩＮＮＩＮＧＯＦＰＯＩＮＴＰＲＯＣＥＳＳＥＳ,ＲＥＶＩＳＩＴＥＤＨＥＳＨＥＮＧＷＵ（何声武）（ＤｅｐａｒｔｍｅｎｔｏｆＭａｔｈｅｍａｔｉｃａｌＳｔａｔｉｓｔｉｃｓ,ＥａｓｔＣｈｉｎａＮｏｒｍａｌＵｎｉｖｅｒｓｉｔｙＳｈａｎｇｈａｉ２０００６２,Ｃ...     

Some properties of convex hulls generated by homogeneous Poisson point processes in an unbounded convex domain

LetC(A) be the convex hull generated by a Poisson point process in an unbounded convex setA. A representation ofAC(A) as the union of curvilinear triangles with independent areas is established. In the case whenA is a cone the properties of the representation are examined more completely. It is also indicated how to simulateC(A) directly without first simulating the process itself.     

Estimation variances for estimators of product densities and pair correlation functions of planar point processes

Approximations of the estimation variances of kernel estimators of the pair correlation function and the product density of a planar Poisson process are given. Furthermore, a heuristic approximation of the estimation variance of an estimator of the pair correlation function of a general planar point process is suggested. All formulae have been tested by simulation experiments.     

Statistical inference for detrended point processes

We consider a multivariate point process with a parametric intensity process which splits into a stochastic factor b_t and a trend function a_t of a squared polynomial form with exponents larger than . Such a process occurs in a situation where an underlying process with intensity b_t can be observed on a transformed time scale only. On the basis of the maximum likelihood estimator for the unknown parameter a detrended (or residual) process is defined by transforming the occurrence times via integrated estimated trend function. It is shown that statistics (mean intensity, periodogram estimator) based on the detrended process exhibit the same asymptotic properties as they do in the case of the underlying process (without trend function). Thus trend removal in point processes turns out to be an appropriate method to reveal properties of the (unobservable) underlying process – a concept which is well established in time series. A numerical example of an earthquake aftershock sequence illustrates the performance of the method.     

Inference for thinned point processes, with application to Cox processes

Given i.i.d. point processes N₁, N₂,…, let the observations be p-thinnings N′₁, N′₂,…, where p is a function from the underlying space E (a compact metric space) to [0, 1], whose interpretation is that a point of N_i at x is retained with probability p(x) and deleted with probability 1−p(x). Strongly consistent estimators of the thinning function p and the Laplace functional L_N(f) = E[e^−N(f)] of the N_i are constructed; associated “central limit” properties are given. Tests are presented, for the case when the N_i and N′_i are both observable, of the hypothesis that the N′_i are p-thinnings of the N_i. State estimation techniques are developed for the case where the N_i are Cox processes directed by unobservable random measures M_i; these techniques yield minimum mean-squared error estimators, based on observation of only the thinned processes N′_i of the N_i and the directing measures M_i. Limit theorems for empirical Laplace functionals of point processes are given.     

Perfect simulation and inference for point processes given noisy observations

Summary  The paper is concerned with the exact simulation of an unobserved true point process conditional on a noisy observation. We use dominated coupling from the past (CFTP) on an augmented state space to produce perfect samples of the target marked point process. An optimized coupling of the target chains makes the algorithm considerable faster than with the standard coupling used in dominated CFTP for point processes. The perfect simulations are used for inference and the results are compared to an ordinary Metropolis-Hastings sampler.     

Partitions of point processes: Multivariate poisson approximations

This study shows that when a point process is partitioned into certain uniformly sparse subprocesses, then the subprocesses are asymptotically multivariate Poisson or compound Poisson. Bounds are given for the total-variation distance between the subprocesses and their limits. Several partitioning rules are considered including independent, Markovian, and batch assignments of points.     

Optimisation of linear unbiased intensity estimators for point processes

A general non-stationary point process whose intensity function is given up to unknown numerical factor λ is considered. As an alternative to the conventional estimator of λ based on counting the points, we consider general linear unbiased estimators of λ given by sums of weights associated with individual points. A necessary and sufficient condition for a linear, unbiased estimator for the intensity λ to have the minimum variance is determined. It is shown that there are “nearly” no other processes than Poisson and Cox for which the unweighted estimator of λ, which counts the points only, is optimal. The properties of the optimal estimator are illustrated by simulations for the Matérn cluster and the Matérn hard-core processes. This research was partially supported by Grant Agency of Czech Republic, project No. 201/03/D062.     

Position dependent and stochastic thinning of point processes

A short probabilistic proof of Kallenberg's theorem [2] on thinning of point processes is given. It is extended to the case where the probability of deletion of a point depends on the position of the point and is itself random. The proof also leads easily to a statement about the rate of convergence in Renyi's theorem on thinning a renewal process.     

Ordered thinnings of point processes and random measures

This is a study of thinnings of point processes and random measures on the real line that satisfy a weak law of large numbers. The thinning procedures have dependencies based on the order of the points or masses being thinned such that the thinned process is a composition of two random measures. It is shown that the thinned process (normalized by a certain function) converges in distribution if and only if the thinning process does. This result is used to characterize the convergence of thinned processes to infinitely divisible processes, such as a compound Poisson process, when the thinning is independent and nonhomogeneous, stationary, Markovian, or regenerative. Thinning by a sequence of independent identically distributed operations is also discussed. The results here contain Renyi's classical thinning theorem and many of its extensions.     

Bounds for the variance of certain stationary point processes

For the variance of stationary renewal and alternating renewal processes N_n(·) the paper establishes upper and lower bounds of the form

$\text{?B}{}_1\text{?varN}{}_8\text{(0,x–Aλx?B}{}_2\text{(0<x<∞)}$

, where λ=EN₈(0,1), with constants A, B₁ and B₂ that depend on the first three moments of the interval distributions for the processes concerned. These results are consistent with the value of the constant A for a general stationary point process suggested by Cox in 1963 [1].     

Estimation for nonhomogeneous Poisson processes from aggregated data

A well-known heuristic for estimating the rate function or cumulative rate function of a nonhomogeneous Poisson process assumes that the rate function is piecewise constant on a set of data-independent intervals. We investigate the asymptotic (as the amount of data grows) behavior of this estimator in the case of equal interval widths, and show that it can be transformed into a consistent estimator if the interval lengths shrink at an appropriate rate as the amount of data grows.     

Neural fuzzy point processes

Synaptic events in neural systems were described as generated by an apparatus @ possessing memory and encoding a fuzzy point process (the presynaptic discharge) into another N (the postsynaptic discharge). @ was considered to be a fuzzy automata, for which state membership is dependent on input membership and distribution as well as on a control exercised by other neural structures. In such a device, irregular input distributions favour a direct monotonic codification, whereas regular ones induce discontinuous and inverse relations between both fuzzy point processes. Both behaviors favour analogic and membership relations between the fuzzy input and output. However, there exist intermediate grades of irregularities which result in a context-free encoding, where similitude and equivalence relations predominate. The importance of such findings to neurophysiology is discussed.     

Estimation of change point for switching fractional diffusion processes

We study the asymptotic distribution of the maximum likelihood estimator (MLE) for the change point for fractional diffusion processes as the noise intensity tends to zero. It was shown that the rate of convergence here is higher than the rate of convergence of the distribution of the MLE in classical parametric models dealing with independent identically distributed observations with finite and positive Fisher information.     

Point processes characterized by their one dimensional distributions

It is well-known that the distribution of a point process defined on a carrier space is uniquely characterised by its finite dimensional joint distributions of counts on disjoint subsets of . In this note, we investigate the common structure of point processes whose distributions are specified by their one dimensional distributions. We also show that, if is such a point process, then a sequence of point processes { _n } converges in distribution to if and only if { _n (B)} converges in distribution to (B) for a suitably rich class of sets B. Supported by ARC Discovery project number DP0209179 Mathmatics Subject Classification (2000):Primary 60G55; Secondary 60E05, 60B10 AcknowledgementI would like to thank a referee for his valuable suggestions on the presentation of this paper.     

Universal point sets for planar three-trees

For every $n\in \mathbb{N}$, we present a set $S_n$ of $O(n^{3/2}\log n)$ points in the plane such that every planar 3-tree with n vertices has a straight-line embedding in the plane in which the vertices are mapped to a subset of $S_n$. This is the first subquadratic upper bound on the cardinality of universal point sets for planar 3-trees, as well as for the class of 2-trees and serial parallel graphs.     

Difference operators and determinantal point processes

The paper deals with a family {P} of determinantal point processes arising in representation theory and random matrix theory. The processes P live on a one-dimensional lattice and have a number of special properties. One of them is that the correlation kernel K(x, y) of each of the processes is a projection kernel: it determines a projection K in the Hilbert ?² space on the lattice. Moreover, the projection K can be realized as the spectral projection onto the positive part of the spectrum of a self-adjoint difference second-order operator D. The aim of the paper is to show that the difference operators D can be efficiently used in the study of limit transitions within the family {P}.     

Area-interaction point processes

We introduce a new Markov point process that exhibits a range of clustered, random, and ordered patterns according to the value of a scalar parameter. In contrast to pairwise interaction processes, this model has interaction terms of all orders. The likelihood is closely related to the empty space functionF, paralleling the relation between the Strauss process and Ripley'sK-function. We show that, in complete analogy with pairwise interaction processes, the pseudolikelihood equations for this model are a special case of the Takacs-Fiksel method, and our model is the limit of a sequence of auto-logistic lattice processes.