Nonparametric estimation of Matusita's measure of affinity between absolutely continuous distributions

LetF andG be two distribution functions defined on the same probability space which are absolutely continuous with respect to the Lebesgue measure with probability densitiesf andg, respectively. Matusita [3] defines a measure of the closeness, affinity, betweenF andG as: . Based on two independent samples fromF andG we propose to estimate ρ by , where and are taken to be the kernel estimates off(x) andg(x), respectively, as given by Parzen [5]. In this note sufficient conditions are given such that (i) asx→∞ and (ii) with probability one, asn→∞. Research supported in part by the National Research Council of Canada and by McMaster University Science and Engineering Research Board. The author is presently with the Department of Mathematical Sciences, Memphis State University, Memphis, Tennessee 38152.     

Nonparametric estimation of distributions with categorical and continuous data

In this paper we consider the problem of estimating an unknown joint distribution which is defined over mixed discrete and continuous variables. A nonparametric kernel approach is proposed with smoothing parameters obtained from the cross-validated minimization of the estimator's integrated squared error. We derive the rate of convergence of the cross-validated smoothing parameters to their ‘benchmark’ optimal values, and we also establish the asymptotic normality of the resulting nonparametric kernel density estimator. Monte Carlo simulations illustrate that the proposed estimator performs substantially better than the conventional nonparametric frequency estimator in a range of settings. The simulations also demonstrate that the proposed approach does not suffer from known limitations of the likelihood cross-validation method which breaks down with commonly used kernels when the continuous variables are drawn from fat-tailed distributions. An empirical application demonstrates that the proposed method can yield superior predictions relative to commonly used parametric models.     

Nonparametric estimation of compound distributions with applications in insurance

A nonparametric estimator of the distribution functionG of a random sum of independent identically distributed random variables, with distribution functionF, is proposed in the case where the distribution of the number of summands is known and a random sample fromF is available. This estimator is found by evaluating the functional that mapsF ontoG at the empirical distribution function based on the random sample. Strong consistency and asymptotic normality of the resulting estimator in a suitable function space are established using appropriate continuity and differentiability results for the functional. Bootstrap confidence bands are also obtained. Applications to the aggregate claims distribution function and to the probability of ruin in the Poisson risk model are presented.     

A measure of discrimination between two residual life-time distributions and its applications

A measure of discrepancy between two residual-life distributions is proposed on the basis of Kullback-Leibler discrimination information. Properties of this measure are studied and the minimum discrimination principle is applied to obtain the proportional hazards model.Northern Illinois University on a professional development leave.     

Super-Brownian motions in higher dimensions with absolutely continuous measure states

Continuous super-Brownian motions in two and more dimensions are known to have singular measure states. However, by weakening the branching mechanism in an irregular way they can be forced to have absolutely continuous states. The sufficient conditions we impose are identified in a couple of examples with irregularities in only one coordinate. This includes the case of branching restricted to some densely situated ensemble of hyperplanes.Supported by an NSERC Grant.     

Characteristic functional of a probability measure absolutely continuous with respect to a Gaussian Radon measure

Let μ and μ₁ be probability measures on a locally convex Hausdorff real topological linear space E. C. R. Baker (Lecture Notes in Mathematics No. 109, pp. 33–44, Springer-Verlag, Berlin/New York, 1979) posed the problem of characterizing the absolute continuity of μ and μ₁ by their characteristic functionals. The aim of this paper is to give an answer to this problem in the case where μ is a Gaussian Radon measure. A Fourier transform shall be defined, the inversion formula established, and then a necessary and sufficient condition given for μ₁ to be absolutely continuous with respect to μ based on the characteristic functional. As applications, for the convolution $\text{μ}{}_1\text{= μ1v}$, where v is a Radon measure on E, we shall give some concrete sufficient conditions on v for $\text{μ1v ? μ}$.     

Decomposition of infinitely divisible characteristic functions with absolutely continuous poisson spectral measure

We shall consider the problem of characterizing infinitely divisible characteristic functions which have only infinitely divisible factors. Infinitely divisible characteristic functions treated in this paper are those which have absolutely continuous Poisson spectral measures and have no Gaussian component in their Lévy canonical representations. It will be shown that Ostrovskii's sufficient condition is also necessary in this case.     

Complexity and asymptotically optimal algorithms for modeling of absolutely continuous distributions

In a paper of Knuth and Yo [Kibern. Sb.,19 (1983)] the question is posed which intermediate model of DG-algorithms (transforming uniformly distributed random bits into random variables with arbitrary distributions) best corresponds to the practically important distributions. The goal of the present paper is the study of one such model for absolutely continuous distributions, which apparently includes both finite and general DG-algorithms.Translated from Zapiski Nauchnykh Seminarov Leningradskogo Otdeleniya Matematicheskogo Instituta im. V. A. Steklova AN SSSR, Vol. 137, pp. 115–123, 1984.     

On the minimality of search paths under absolutely continuous univariate distributions

The linear search problem is concerned with the search for a target located randomly on a line. The target being sought for might be on either side of some starting point. A searcher makes for the target with an upper bound on his speed, using a continuous search path in which he changes his direction many times before reaching his goal. The minimality of average distance (time) from the starting point upon reaching the target is the measure of optimality of search paths. We have obtained sufficient conditions that guarantee the minimality of such search paths whenever the target has an absolutely continuous distribution.

---

Zusammenfassung Ein Objekt, das sich in zufälliger Position auf einer Strecke befindet, soll gesucht werden; der Startpunkt liegt im Inneren der Strecke. Für die Bewegungsgeschwindigkeit bei der Suche ist eine obere Schranke gegeben; der Suchpfad muß stetig sein, wobei beliebig viele Richtungsänderungen zugelassen sind. Das Ziel ist die Minimierung der erwarteten Zeit bis zum Erreichen des Objekts. Unter der Voraussetzung einer absolut stetigen Verteilung für die Position des Objekts werden hinreichende Bedingungen für die Optimalität eines Suchpfades angegeben.

     

On the measure of the absolutely continuous spectrum for Jacobi matrices

We apply the methods of classical approximation theory (extreme properties of polynomials) to study the essential support ${\Sigma }_{\mathrm{ac}}$ of the absolutely continuous spectrum of Jacobi matrices. First, we prove an upper bound on the measure of ${\Sigma }_{\mathrm{ac}}$ which takes into account the value distribution of the diagonal elements, and implies the bound due to Deift–Simon and Poltoratski–Remling.Second, we generalise the differential inequality of Deift–Simon for the integrated density of states associated with the absolutely continuous spectrum to general Jacobi matrices.     

Nonparametric estimation and testing time-homogeneity for processes with independent increments

We consider a nonparametric estimation problem for the Lévy measure of time-inhomogeneous process with independent increments. We derive the functional asymptotic normality and efficiency, in an ℓ^∞-space, of generalized Nelson–Aalen estimators. Also we propose some asymptotically distribution free tests for time-homogeneity of the Lévy measure. Our result is a fruit of the empirical process theory and the martingale theory.     

Testing hypotheses about the equality of several risk measure values with applications in insurance

This paper explores statistical tests about the equality of risk measure values obtained using a distortion-based risk measure. We consider both the case in which the risk measure value is specified in the null hypothesis and the case in which it is not. In the former case, one- and two-sided alternatives are considered, and in the latter case, ordered and unordered alternatives are considered. Asymptotically most powerful tests are obtained, and asymptotic distributions of the test statistics are found using results about the asymptotic distributions of the risk measure values. Finally, we consider a numerical example and conclude the paper with notes on when the results of the paper could, or could not, be safely used.     

On the coexistence of absolutely continuous and singular continuous components of the spectral measure for some Sturm-Liouville operators with square summable potential

We prove that there exist some Sturm-Liouville operators with square summable potentials such that the singular continuous component of the spectral measure lies on the positive half-line. The Hausdorff dimension of the support of this singular measure can be arbitrary number from 0 to 1.     

Nonparametric estimation of an extreme-value copula in arbitrary dimensions

Inference on an extreme-value copula usually proceeds via its Pickands dependence function, which is a convex function on the unit simplex satisfying certain inequality constraints. In the setting of an i.i.d. random sample from a multivariate distribution with known margins and an unknown extreme-value copula, an extension of the Capéraà-Fougères-Genest estimator was introduced by D. Zhang, M. T. Wells and L. Peng [Nonparametric estimation of the dependence function for a multivariate extreme-value distribution, Journal of Multivariate Analysis 99 (4) (2008) 577-588]. The joint asymptotic distribution of the estimator as a random function on the simplex was not provided. Moreover, implementation of the estimator requires the choice of a number of weight functions on the simplex, the issue of their optimal selection being left unresolved.A new, simplified representation of the CFG-estimator combined with standard empirical process theory provides the means to uncover its asymptotic distribution in the space of continuous, real-valued functions on the simplex. Moreover, the ordinary least-squares estimator of the intercept in a certain linear regression model provides an adaptive version of the CFG-estimator whose asymptotic behavior is the same as if the variance-minimizing weight functions were used. As illustrated in a simulation study, the gain in efficiency can be quite sizable.     

The composition of Wiener functionals with non absolutely continuous Shifts

Summary In this paper we study some classes of Wiener functionals whose elements can be composed with a non-linear, non-absolutely continous transformation of the form of perturbation of identity in the direction of Cameron-Martin space. We show that under certain conditions the image of the Wiener measure under the above transformation induces a generalized Wiener functional on certain Sobolev spaces generalizing the Radon-Nikodym relation to non absolutely continuous transformations. A series representation for the generalized Radon-Nikodym derivative is presented and conditional expectations of some generalized random variables are considered.     

Large deviation theorems in the problem of testing two simple hypotheses

Limit theorems on large deviations of the logarithm of the likelihood ratio are proved for the problem of distinguishing two simple hypotheses in the general scheme of statistical experiments under the null hypothesis and under an alternative hypothesis. The theorems obtained are applied to the investigation of a decrease in the probability of errors of the first and second kind for the Neumann-Pearson criterion.Translated from Ukrainskii Matematicheskii Zhurnal, Vol. 47, No. 2, pp. 227–235, February, 1995.