Spectral tail processes and max-stable approximations of multivariate regularly varying time series

A regularly varying time series as introduced in Basrak and Segers (2009) is a (multivariate) time series such that all finite dimensional distributions are multivariate regularly varying. The extremal behavior of such a process can then be described by the index of regular variation and the so-called spectral tail process, which is the limiting distribution of the rescaled process, given an extreme event at time 0. As shown in Basrak and Segers (2009), the stationarity of the underlying time series implies a certain structure of the spectral tail process, informally known as the “time change formula”. In this article, we show that on the other hand, every process which satisfies this property is in fact the spectral tail process of an underlying stationary max-stable process. The spectral tail process and the corresponding max-stable process then provide two complementary views on the extremal behavior of a multivariate regularly varying stationary time series.     

On a bivariate copula with both upper and lower full-range tail dependence

Copula functions can be useful in accounting for various dependence patterns appearing in joint tails of data. We propose a new two-parameter bivariate copula family that possesses the following features. First, both upper and lower tails are able to explain full-range tail dependence. That is, the dependence in each tail can range among quadrant tail independence, intermediate tail dependence, and usual tail dependence. Second, it can capture upper and lower tail dependence patterns that are either the same or different. We first prove the full-range tail dependence property, and then we obtain the corresponding extreme value copula. There are two applications based on the proposed copula. The first one is modeling pairwise dependence between financial markets. The second one is modeling dynamic tail dependence patterns that appear in upper and lower tails of a loss-and-expense data.     

Equivalence classes of regularly varying functions

A useful method to derive limit results for partial maxima and record values of independent, identically distributed random variables is to start from one specific probability distribution and to extend the result for this distribution to a class of distributions.This method involves an extended theory of regularly varying functions. In this paper, equivalence classes of regularly varying functions (in the extended sense) are studied, which is relevant to the problems mentioned above.     

Fitting and validation of a bivariate model for large claims

We consider an extended version of a model proposed by Ledford and Tawn [Ledford, A.W., Tawn, J.A., 1997. Modelling dependence within joint tail regions. J. R. Stat. Soc. 59 (2), 475-499] for the joint tail distribution of a bivariate random vector, which essentially assumes an asymptotic power scaling law for the probability that both the components of the vector are jointly large. After discussing how to fit the model, we devise a graphical tool that analyzes the differences between certain empirical probabilities and model based estimates of the same probabilities. The asymptotic normality of these differences allows the construction of statistical tests for the model assumption. The results are applied to claims of a Danish fire insurance and to medical claims from US health insurances.     

The canonical decomposition of bivariate distributions

The ordinary notion of a bivariate distribution has a natural generalisation. For this generalisation it is shown that a bivariate distribution can be characterised by a Hilbert space and a family _p, 0 ≤ p ≤ 1, of subspaces of . specifies the marginal distributions whilst _p is a summary of the dependence structure. This characterisation extends existing ideas on canonical correlation.     

Positive solutions of fourth order Emden-Fowler type differential equations in the framework of regular variation

The fourth order nonlinear differential equations

(A)     

Expansions and penultimate distributions of maxima of bivariate normal random vectors

It is well known that the marginal maxima of n$n$ standard normal random vectors with correlation coefficient ρ<1$\rho <1$ are asymptotically independent. In this article, the residual dependence will be captured by asymptotic expansions and certain penultimate distributions including the case where ρ(n)↑1$\rho \left(n\right)\uparrow 1$ at a certain rate.     

Tail fit and the Zipf–Pareto law

A limit theorem with bounds on the rate of convergence is proven. The joint distribution of a fixed number of relative decrements of the top order statistics from a random sample converges to the limit as the sample size increases if and only if the underlying distribution is in essence a Pareto. In conjunction with a chi-square test of fit, it provides an asymptotically distribution-free test of fit to the family of distributions with regularly varying tails at infinity. When the limit distribution holds, rank-size plots obey Zipf’s law. The test can be used to detect departures from this Zipf–Pareto law.      

On the max-domain of attractions of bivariate elliptical arrays

Let be a triangular array of independent bivariate elliptical random vectors with the same distribution function as where is a bivariate spherical random vector. Under assumptions on the speed of convergence of we show in this paper that the maxima of this triangular array is in the max-domain of attraction of a new max-id. distribution function , provided that has distribution function in the max-domain of attraction of the Weibull distribution function . AMS 2000 Subject Classification Primary—60G70, 60F05     

An integro-local theorem applicable on the whole half-axis to the sums of random variables with regularly varying distributions

We obtain an integro-local limit theorem for the sum S(n) = ξ(1)+?+ξ(n) of independent identically distributed random variables with distribution whose right tail varies regularly; i.e., it has the form P(ξ≥t) = t ^?β L(t) with β > 2 and some slowly varying function L(t). The theorem describes the asymptotic behavior on the whole positive half-axis of the probabilities P(S(n) ∈ [x, x + Δ)) as x → ∞ for a fixed Δ > 0; i.e., in the domain where the normal approximation applies, in the domain where S(n) is approximated by the distribution of its maximum term, as well as at the “junction” of these two domains.     

On limit laws for sums of Pfeifer records

The problem of determining limiting distributions for sums of records has been studied by several authors who have considered a variety of assumptions sufficient to ensure that sums of records properly normalized will converge to a non-degenerate distribution. As a parallel to these endeavors, it is of interest to establish conditions under which the sum of Pfeifer records, properly normalized, converges. Pfeifer records are defined under the assumption that initial observations are i.i.d. with common survival function and following the (n−1)-th record value the observations are assumed to have survival function ,n=1,2,.... The study of the asymptotic behavior of sums of Pfeifer records constitutes a natural generalization of work on sums of classical records. The present paper introduces conditions under which the limit distribution of sums of Pfeifer records is non-degenerate.      

On non-null distributions connected with testing that a real normal distribution is complex

The exact and the asymptotic non-null distribution of the maximal invariant corresponding to testing that the covariance matrix of a 2m-dimensional real normal distribution has complex structure is obtained.     

A representation of bivariate extreme value distributions via norms on \mathbb{R}^{2}

It is known that a bivariate extreme value distribution (EVD) with reverse exponential margins can be represented as , , where is a suitable norm on . We prove in this paper the converse implication, i.e., given an arbitrary norm on , , , defines an EVD with reverse exponential margins, if and only if the norm satisfies for the condition . This result is extended to bivariate EVDs with arbitrary margins as well as to extreme value copulas. By identifying an EVD , , with the unit ball corresponding to the generating norm , we obtain a characterization of the class of EVDs in terms of compact and convex subsets of .     

The bivariate noncentral chi-square distribution - A compound distribution approach

This paper proposes the bivariate noncentral chi-square (BNC) distribution by compounding the Poisson probabilities with the bivariate central chi-square distribution. The probability density and cumulative distribution functions of the joint distribution of the two noncentral chi-square variables are derived for arbitrary values of the correlation coefficient, degrees of freedom(s), and noncentrality parameters. Computational procedures to calculate the upper tail probabilities as well as the percentile points for selected values of the parameters, for both equal and unequal degrees of freedom, are discussed. The graphical representation of the distribution for different values of the parameters are provided. Some applications of the distribution are outlined.     

The normal famility of mermorphic functions

Let F be a family of mermorphic functions in a domain D, and let a, b, c be complex numbers, a ≠ b. If for each f ∈ F, the zeros of f-c are of multiplicity ≥ k ＋ 1, and -↑Ef（k）（a） belong to -↑Ef （a）, -↑Ef（k）（b）belong to -↑Ef （b）, then F is normal in D.     

Optimizing an objective function under a bivariate probability model

The motivation of this paper is to obtain an analytical closed form of a quadratic objective function arising from a stochastic decision process with bivariate exponential probability distribution functions that may be dependent. This method is applicable when results need to be offered in an analytical closed form without double integrals. However, the study only applies to cases where the correlation coefficient between the two variables is positive or null. A stochastic, stationary objective function, involving a single decision variable in a quadratic form is studied. We use a primitive of a bivariate exponential distribution as first expressed by Downton [Downton, F., 1970. Bivariate exponential distributions in reliability theory. Journal of Royal Statistical Society B 32, 408–417] and revisited in Iliopoulos [Iliopoulos, George., 2003. Estimation of parametric functions in Downton’s bivariate exponential distribution. Journal of statistical planning and inference 117, 169–184]. With this primitive, optimization of objective functions in Operations Research, supply chain management or any other setting involving two random variables, or calculations which involve evaluating conditional expectations of two joint random variables are direct. We believe the results can be extended to other cases where exponential bivariates are encountered in economic objective function evaluations. Computation algorithms are offered which substantially reduce computation time when solving numerical examples.     

The generalized Cantor distribution and its corresponding inverse distribution

Building on ideas and concepts introduced by Lad, Taylor and Hosking, a generalized Cantor distribution and a corresponding skew generalized Cantor distribution are developed and analyzed. Associated inverse distributions are also introduced. In some cases method of moment estimation is shown to be readily implemented.     

The q-asymptotic function in c-convex analysis

Abstract

We establish several connections between generalized asymptotic functions and different areas of convexity theory, without coercivity assumptions. Properties and characterizations of abstract subdifferentials, normal cones, conjugates, support functions and optimality conditions for the minimization problem are given. We provide a new result on existence of minimizers for a class of nonconvex functions which is strictly larger than the class of quasiconvex ones.