Parameter Estimation for Inhomogeneous Space‐Time Shot‐Noise Cox Point Processes

We consider the problem of parameter estimation for inhomogeneous space‐time shot‐noise Cox point processes. We explore the possibility of using a stepwise estimation method and dimensionality‐reducing techniques to estimate different parts of the model separately. We discuss the estimation method using projection processes and propose a refined method that avoids projection to the temporal domain. This remedies the main flaw of the method using projection processes – possible overlapping in the projection process of clusters, which are clearly separated in the original space‐time process. This issue is more prominent in the temporal projection process where the amount of information lost by projection is higher than in the spatial projection process. For the refined method, we derive consistency and asymptotic normality results under the increasing domain asymptotics and appropriate moment and mixing assumptions. We also present a simulation study that suggests that cluster overlapping is successfully overcome by the refined method.     

Predictive information and distance between past and future of a time series

A characterization for the nullity of the cosine angle between two subspaces of a Hilbert space is established. Given a time series x, we use this characterization in order to investigate the relationship between the notions of predictor space and distance between the information contained in the past and in the future of x. In particular, we prove that the predictor space of x coincides with the zero vector space {0} if and only if this distance achieves its maximum value.     

A Fixed Point Approach to Solve the Average Cost Optimality Equation for Semi-Markov Decision Processes with Feller Transition Probabilities

Semi-Markov control processes with Feller (also known as weakly continuous) transition probabilities and unbounded cost functions are considered. We give sufficient conditions for the existence of a lower semicontinuous and continuous solutions to the average cost optimality equation. The proof is based on a fixed point argument.     

Model Order Estimation of a Multivariable Stochastic Process

ABSTRACT

This article presents a procedure allowing us to estimate the minimal order of a state-space representation, for a multivariable stochastic process, from a sequence of observations. The method proposes a statistical rule for testing the rank of a block Hankel matrix of data, since this rank is related to the order of the process. A new information criterion is then developed and used to decide upon the order of the model. In this article we generalize the Aoki C-test. Using two representative data sets as the basis for a Monte Carlo experiment and real data based on Danish economy, we estimate the order of multivariable stochastic processes.     

Modeling spatial overdispersion via the generalized Waring point process

Modeling spatial overdispersion requires point process models with finite‐dimensional distributions that are overdisperse relative to the Poisson distribution. Fitting such models usually heavily relies on the properties of stationarity, ergodicity, and orderliness. In addition, although processes based on negative binomial finite‐dimensional distributions have been widely considered, they typically fail to simultaneously satisfy the three required properties for fitting. Indeed, it has been conjectured by Diggle and Milne that no negative binomial model can satisfy all three properties. In light of this, we change perspective and construct a new process based on a different overdisperse count model, namely, the generalized Waring (GW) distribution. While comparably tractable and flexible to negative binomial processes, the GW process is shown to possess all required properties and additionally span the negative binomial and Poisson processes as limiting cases. In this sense, the GW process provides an approximate resolution to the conundrum highlighted by Diggle and Milne.     

Estimating a covariance function having an un unknown scale kakameter

The structure of a family ρ of measures corresponding to a zero-mean Gaussian process with covariance αR(s,t) is discussed. When R itself is known (R and T completely arbitrary), it is shown that ρ is either homogeneous or composed of singular measures, depending on whether the reproducing kernel Hilbert space H(R,T) is finite- or infinite-dimensional. For the case dim H < ∞ the MLE α is given; when dim H = ∞ an almost sure discriminator is constructed. More generally, it is shown that when R itself depends upon a parameter θ (not necessarily a scalar) and certain broad assumptions are met, one may describe the orthogonal decomposition of P and estimate both a and θ.     

Asymptotically Distribution-Free Goodness-of-Fit Testing: A Unifying View

We outline a general paradigm for constructing asymptotically distribution-free (ADF) goodness-of-fit tests, which can be regarded as a generalization of Khmaladze (1993 Khmaladze , E. V. ( 1993 ). Goodness of fit problem and scanning innovation martingales . Ann. Statist. 21 ( 2 ): 798 – 829 .[Crossref], [Web of Science ®] , [Google Scholar]). This is achieved by a nonorthogonal projection of a class of functions onto the ortho-complement of the extended tangent space (ETS) associated with the null hypothesis. In parallel with the work of Bickel et al. (2006 Bickel , P. J. , Ritov , Y. , Stoker , T. M. ( 2006 ). Tailor-made tests for goodness of fit to semiparametric hypotheses . Ann. Statist. 34 ( 2 ): 721 – 741 . [Google Scholar]), we obtain transformed empirical processes (TEP) which are the building blocks for constructing omnibus tests such as the usual Kolmogorov–Smirnov type tests and Crámer–von Mise type tests, as well as Portmanteau tests and directional tests. The critical values can be tabulated due to the ADF property. All the tests are capable of detecting local (Pitman) alternative at the root-n scale. We shall illustrate the framework in several examples, mostly in regression model specification testing.     

The ARHD model

We introduce and study a new model for functional data. The ARHD is an autoregressive model in which the first order derivative of the random curves appears explicitly. Convergent estimates are obtained through an original double penalization method. The prediction method is applied to a real set of data already studied in the literature.     

Wavelets for Nonparametric Stochastic Regression with Mixing Stochastic Process

We propose a wavelet based stochastic regression function estimator for the estimation of the regression function for a sequence of mixing stochastic process with a common one-dimensional probability density function. Some asymptotic properties of the proposed estimator are investigated. It is found that the estimators have similar properties to their counterparts studied earlier in literature.     

A Stochastic Geometry Model for Functional Magnetic Resonance Images

In functional magnetic resonance imaging, spatial activation patterns are commonly estimated using a non-parametric smoothing approach. Significant peaks or clusters in the smoothed image are subsequently identified by testing the null hypothesis of lack of activation in every volume element of the scans. A weakness of this approach is the lack of a model for the activation pattern; this makes it difficult to determine the variance of estimates, to test specific neuroscientific hypotheses or to incorporate prior information about the brain area under study in the analysis. These issues may be addressed by formulating explicit spatial models for the activation and using simulation methods for inference. We present one such approach, based on a marked point process prior. Informally, one may think of the points as centres of activation, and the marks as parameters describing the shape and area of the surrounding cluster. We present an MCMC algorithm for making inference in the model and compare the approach with a traditional non-parametric method, using both simulated and visual stimulation data. Finally we discuss extensions of the model and the inferential framework to account for non-stationary responses and spatio-temporal correlation.     

BERNOULLI SAMPLING

The concepts of the Bernoulli count process of a point process and Bernoulli sampling of a discrete parameter stochastic process are introduced. The Bernoulli count process determines the stochastic structure of the point process, and a process obtained by thinning a discrete parameter stochastic process by Bernoulli sampling satisfies the same property. Stationarity and the Markov property remain invariant under Bernoulli sampling.     

On semi-markov compartmental models with branching particles under the influence of disasters

A semi-Markov multi-compart mental system in which particles reproduce similar particles as a Markov branching process and being subjected to disasters is studied. Expressions for the mean number of particles alive at time t in each compartment are obtained. The results concerning irreversible, mammillarian and catenary compartmental systems have been discussed.     

A nonparametric bayesian approach to analysis of drug dependence data

In this paper, a nonparametric Bayesian approach to the analysis of binary response data is considered. Using a Dirichlet process prior, and squared error loss, the Bayes estimators of response probabilities are obtained. Finally, the results obtained are employed to analyze the ARC 090 Trial data.     

Markov Beta and Gamma Processes for Modelling Hazard Rates

This paper generalizes the discrete time independent increment beta process of Hjort (1990 ), for modelling discrete failure times, and also generalizes the independent gamma process for modelling piecewise constant hazard rates ( Walker and Mallick, 1997 ). The generalizations are from independent increment to Markov increment prior processes allowing the modelling of smoothness. We derive posterior distributions and undertake a full Bayesian analysis.     

Conditional probability and improper priors

ABSTRACT

According to Jeffreys improper priors are needed to get the Bayesian machine up and running. This may be disputed, but usage of improper priors flourish. Arguments based on symmetry or information theoretic reference analysis can be most convincing in concrete cases. The foundations of statistics as usually formulated rely on the axioms of a probability space, or alternative information theoretic axioms that imply the axioms of a probability space. These axioms do not include improper laws, but this is typically ignored in papers that consider improper priors.

The purpose of this paper is to present a mathematical theory that can be used as a foundation for statistics that include improper priors. This theory includes improper laws in the initial axioms and has in particular Bayes theorem as a consequence. Another consequence is that some of the usual calculation rules are modified. This is important in relation to common statistical practice which usually include improper priors, but tends to use unaltered calculation rules. In some cases, the results are valid, but in other cases inconsistencies may appear. The famous marginalization paradoxes exemplify this latter case.

An alternative mathematical theory for the foundations of statistics can be formulated in terms of conditional probability spaces. In this case, the appearance of improper laws is a consequence of the theory. It is proved here that the resulting mathematical structures for the two theories are equivalent. The conclusion is that the choice of the first or the second formulation for the initial axioms can be considered a matter of personal preference. Readers that initially have concerns regarding improper priors can possibly be more open toward a formulation of the initial axioms in terms of conditional probabilities. The interpretation of an improper law is given by the corresponding conditional probabilities.     

Estimating capability index cpk for processes with asymmetric tolerances

Pearn and Chen (1996) considered the process capability index C_pk, and investigated the statistical properties of its natural estimator under various process conditions. Their investigation, however, was restricted to processes with symmetric tolerances. Recently, Pearn and Chen (1998) considered a generalization of C_pk, referred to as C^? _pk, to cover processes with asymmetric tolerances. They investigated the statistical properties of the natural estimator of C^? _pk, and obtained the exact formulae for the expected value and variance. In this paper, we consider a new estimator of C^? _pk, assuming the knowledge on P(LI > T) = p is available, where 0 > p > 1, which can be obtained from historical information of a stable process. We obtain the exact distribution of the new estimator assuming the process characteristic follows the normal distribution. We show that the new estimator is consistent, asymptotically unbiased, which converges to a mixture of two normal distributions. We also show that by adding suitable correction factors to the new estimator, we may obtain the UMVUE and the MLE of the generalization C^? _pk.     

Information loss on the mean for spatial processes when some values are missing

The loss of information on the mean due to the presence of missing values is discussed for a Gaussian univariate process on a rectangular lattice. The exact as well as the approximate formulae for this loss are given for general conditional autoregressive (CAR) and simultaneous autoregressive (SAR) processes. The formulae are evaluated for some low order CAR and SAR processes. The approximate formula is shown to give a good insight into how the loss varies over the different configurations of missing sites.     

Maximizing Probability Bounds Under Moment-Matching Restrictions

The problem of characterizing a distribution by its moments dates to work by Chebyshev in the mid-nineteenth century. There are clear (and close) connections with characteristic functions, moment spaces, quadrature, and other very classical mathematical pursuits. Lindsay and Basak posed the specific question of how far from normality could a distribution be if it matches k normal moments. They provided a bound on the maximal difference in cdfs, and implied that these bounds were attained. It will be shown here that in fact the bound is not attained if the number of even moments matched is odd. An explicit solution is developed as a symmetric distribution with a finite number of mass points when the number of even moments matched is even, and this bound for the even case is shown to hold as an explicit limit for the subsequent odd case. As Lindsay noted, the discrepancies can be sizable even for a moderate number of matched moments. Some comments on implications are proffered.     

An Immigration-Death Process with a Time-Dependent Delay

In this article, a non homogeneous immigration-death process with delay in the death rate parameter is considered. A process with a time-dependent delay is developed and shown to result in a non homogeneous Poisson process.