位置参数分布族中Fiducial分布与后验分布的关系

本文考虑本质位置参数分布族中,参数的Fiducial分布与后验分布的等同问题．首先讨论了如何给出Fiducial分布,分析结果表明以分布函数形式给出Fiducial分布要比密度函数形式合理,同时,证明了所给的Fiducial分布具有频率性质．然后,研究在参数受到单侧限制时,Fiducial分布与后验分布等同的问题,给出的充要条件是分布族为指数分布族,此时,先验分布是一个广义先验分布,它不能被Lebesgue测度控制．最后,证明了在参数限制在一个有限区间内时,Fiducial分布与任何先验(包括广义先验分布)下的后验分布不等同．     

On the characterization of fisher information and stability of the least favorable lattice distributions

The paper is concerned with the stability properties of the least favorable distributions minimizing the Fisher information in a given class of distributions. The derivation of a least favorable distribution (the solution of a variational problem) is a necessary stage of the Huber minimax approach in robust estimation of a location parameter. Generally, the solutions of variational problems essentially depend on the regularity restrictions of a functional class. The stability of these optimal solutions to violations of the smoothness restrictions is studied under the lattice distribution classes. The discrete analogues of Fisher information are obtained in these cases. They have the form of the Hellinger metrics with the estimation of a real continuous location parameter and the form of the X² metrics with the estimation of an integer discrete location parameter. The analytical expressions for the corresponding least favorable discrete distributions are derived in some classes of lattice distributions by means of generating functions and Bellman's recursive functional equations of dynamic programming. These classes include the class of nondegenerate distributions with a restriction on the value of the density in the center of symmetry, the class of finite distributions, and the class of contaminated distributions. The obtained least favorable lattice distributions preserve the structure of their prototypes in the continuous case. These results show the stability of robust minimax solutions under different types of transitions from the continuous distribution to the discrete one. Proceedings of the Seminar on Stability Problems for Stochastic Models, Hajduszoboszló, Hungary, 1997, Part II.     

Random locations of periodic stationary processes

We consider a family of random locations, called intrinsic location functionals, of periodic stationary processes. This family includes but is not limited to the location of the path supremum and first/last hitting times. We first show that the set of all possible distributions of intrinsic location functionals for periodic stationary processes is the convex hull generated by a specific group of distributions. We then focus on two special subclasses of these random locations. For the first subclass, the density has a uniform lower bound; for the second subclass, the possible distributions are closely related to the concept of joint mixability.     

A representation for the posterior distribution of the location of a moving target

A target moves according to a continuous stochastic process in Euclidean R_^H. A search is conducted by choosing a search strategy and by observing the state of a detection process. Methods for representing the posterior distributions for target location given no detection are discussed. In particular, methods for parameterizing Gaussian models for target motion and the transition intensity of the detection process which yield tractable representations are introduced. The methodology is discussed in terms of two examples.     

Double shrinkage estimation of ratio of scale parameters

The problems of estimating ratio of scale parameters of two distributions with unknown location parameters are treated from a decision-theoretic point of view. The paper provides the procedures improving on the usual ratio estimator under strictly convex loss functions and the general distributions having monotone likelihood ratio properties. In particular,double shrinkage improved estimators which utilize both of estimators of two location parameters are presented. Under order restrictions on the scale parameters, various improvements for estimation of the ratio and the scale parameters are also considered. These results are applied to normal, lognormal, exponential and pareto distributions. Finally, a multivariate extension is given for ratio of covariance matrices.     

Statistical inference for a certain class of bivariate distributions

The paper deals with statistical inference for a certain class of bivariate distributions. The class of marginal distributions is given and is shown to include distributions with only location and scale parameters. A normalizing transformation is applied to the marginal distributions and the parameters are estimated by maximum likelihood. For this class there is a great deal of simplification in the calculations for the asymptotic covariance matrix of the vector of parameter estimators. Statistics for tests of zero correlation are discussed. Also, the analysis is carried out for exponential marginal distributions.     

Goodness-Of-Fit Tests Based on Estimated Expectations of Probability Integral Transformed Order Statistics

New goodness-of-fit tests, based on bootstrap estimated expectations of probability integral transformed order statistics, are derived for the location-scale model. The resulting test statistics are location and scale invariant, and are sensitive to discrepancies at the tails of the hypothesized distribution. The limiting null distributions of the test statistics are derived in terms of functionals of a certain Gaussian process, and the tests are shown to be consistent against a broad family of alternatives. Critical points for all sample sizes are provided for tests of normality. A simulation study shows that the proposed tests are more powerful than established tests such as Shapiro-Wilk, Cramér-von Mises and Anderson-Darling, for a wide range of alternative distributions.     

Measures of location in the plane

Summary There are many possible candidates for measures of location of asymmetric probability distributions. This difficulty is compounded for multivariate distributions. It is the purpose of this paper to characterize the set of all possible measures of location for a given bivariate probability distribution. A closed, convex region in the plane will be constructed, any point of which is a reasonable measure of location. Reasonable here refers to the invariance of the region under certain transformations and order relations. The size of this region can be used to characterize the degree of asymmetry that a distribution possesses.     

On testing the log-gamma distribution hypothesis by bootstrap

In this paper we propose two bootstrap goodness of fit tests for the log-gamma distribution with three parameters, location, scale and shape. These tests are built using the properties of this distribution family and are based on the sample correlation coefficient which has the property of invariance with respect to location and scale transformations. Two estimators are proposed for the shape parameter and show that both are asymptotically unbiased and consistent in mean-squared error. The test size and power is estimated by simulation. The power of the two proposed tests against several alternative distributions is compared to that of the Kolmogorov-Smirnov, Anderson-Darling, and chi-square tests. Finally, an application to data from a production process of carbon fibers is presented.     

Information Inequalities for the Bayes Risk for a Family of Non-Regular Distributions

For a family of non-regular distributions with a location parameter including the uniform and truncated distributions, the stochastic expansion of the Bayes estimator is given and the asymptotic lower bound for the Bayes risk is obtained and shown to be sharp. Some examples are also given.     

An approximation scheme for quasi-stationary distributions of killed diffusions

In this paper we study the asymptotic behavior of the normalized weighted empirical occupation measures of a diffusion process on a compact manifold which is killed at a smooth rate and then regenerated at a random location, distributed according to the weighted empirical occupation measure. We show that the weighted occupation measures almost surely comprise an asymptotic pseudo-trajectory for a certain deterministic measure-valued semiflow, after suitably rescaling the time, and that with probability one they converge to the quasi-stationary distribution of the killed diffusion. These results provide theoretical justification for a scalable quasi-stationary Monte Carlo method for sampling from Bayesian posterior distributions.     

Finite-sample distribution of regression quantiles

The finite-sample distributions of the regression quantile and of the extreme regression quantile are derived for a broad class of distributions of the model errors, even for the non-i.i.d case. The distributions are analogous to the corresponding distributions in the location model; this again confirms that the regression quantile is a straightforward extension of the sample quantile. As an application, the tail behavior of the regression quantile is studied.     

A generalization of Lehmann’s Theorem on the comparison of uniform location experiments

Summary We generalize a result of Lehmann on the comparison of location experiments with uniform distributions on intervals. We compare a location experiment consisting of uniform distributions on parallelepipeds with a location experiment consisting of uniform distributions on convex bodies. We show that the first experiment can only be more informative than the second one if the convex bodies in the second experiment are themselves parallelepipeds. Further we show that the length of the edges of these parallelepipeds must fulfill a condition similar to the condition on the length of the intervals in Lehmanns result.     

One Sample Tests for the Location of Modes of Nonnormal Data

There are few techniques available for testing if modes take specified values. We show that standard tests of location such as the t-test and the Wilcoxon test, which test for the mean and median respectively, can perform poorly as tests for modes when the data is other than unimodal and symmetric. Carolan and Rayner [1] proposed a score test of location for symmetric nonnormal data. We consider a family of distributions similar to those considered by Carolan and Rayner [1] and propose a test for the mode or modes of data from multimodal or skewed distributions and demonstrate by way of simulations that it is reasonably effective.     

On the Parametrization of the Afocal Stable Distributions

Thanks to Hall's documentation of a situation he described asa ‘Comedy of errors’ in the earlier literature onstable distributions, there is now general agreement as to theparametrization of these distributions when standardized asto location and scale. However, two subtly different parametrizationsof location and scale remain current in the afocal stable cases,defined as those with characteristic exponent = 1 and skewnessparameter ß 0. The more widely used parametrization,adopted by Hall and two recent monographs, lacks the linearityproperty that is ordinarily expected of location and scale parameters.This note shows that the alternative parametrization has thislinearity property, and compares the implications of the twoparametrizations for properties of stable distributions. A thirdrecent monograph seeks to avoid these issues by denying thatthe afocal stable distributions are stable at all, but it isshown that they are, in fact, integral members of the stablefamily.     

Loss Estimation for Spherically Symmetrical Distributions

In this paper we consider the problem of estimating the quadratic loss of point estimators of a location parameter for a family of spherically symmetric distributions. We compare the unbiased loss estimator of the minimax estimator with a new shrinkage type loss estimator. Conditions on the distributions for the domination of competing estimators are given. It is shown that, in addition to the class of scale mixtures of normal distributions, there exists a more general family for which the domination results hold.     

Prediction and Inference for Truncated Spatial Data

Abstract

Spatial data in mining, hydrology, and pollution monitoring commonly have a substantial proportion of zeros. One way to model such data is to suppose that some pointwise transformation of the observations follows the law of a truncated Gaussian random field. This article considers Monte Carlo methods for prediction and inference problems based on this model. In particular, a method for computing the conditional distribution of the random field at an unobserved location, given the data, is described. These results are compared to those obtained by simple kriging and indicator cokriging. Simple kriging is shown to give highly misleading results about conditional distributions; indicator cokriging does quite a bit better but still can give answers that are substantially different from the conditional distributions. A slight modification of this basic technique is developed for calculating the likelihood function for such models, which provides a method for computing maximum likelihood estimates of unknown parameters and Bayesian predictive distributions for values of the process at unobserved locations.     

Continuous location model of a rectangular barrier facility

This paper develops a bi-objective model for determining the location, size, and shape of a finite-size facility. The objectives are to minimize both the closest and barrier distances. The closest distance represents the accessibility of customers, whereas the barrier distance represents the interference to travelers. The distributions of the closest and barrier distances are derived for a rectangular facility in a rectangular city where the distance is measured as the rectilinear distance. The analytical expressions for the distributions demonstrate how the location, size, and shape of the facility affect the closest and barrier distances. A numerical example shows that there exists a trade-off between the closest and barrier distances.     

The influence function of the Stahel–Donoho estimator of multivariate location and scatter

This article derives the influence function of the Stahel–Donoho estimator of multivariate location and scatter for elliptical distributions. Local robustness and asymptotic relative efficiency are studied. The expressions obtained for the influence functions coincide with those of one-step reweighted estimators.