Multivariate Discrete Distributions with a Product-Type Dependence

A discrete multivariate probability distribution for dependent random variables, which contains the Poisson and Geometric conditionals distributions as particular cases, is characterized by means of conditional expectations of arbitrary one-to-one functions. Independence of the random variables is also characterized in terms of these conditional expectations. For certain exchangeable and partially exchangeable random variables with a joint distribution of this form it is shown that maximum likelihood estimates coincide with the simple method of moments estimates, suggesting that these models offer a pragmatic way to analyze certain dependent data.     

MM Algorithms for Some Discrete Multivariate Distributions

The MM (minorization–maximization) principle is a versatile tool for constructing optimization algorithms. Every EM algorithm is an MM algorithm but not vice versa. This article derives MM algorithms for maximum likelihood estimation with discrete multivariate distributions such as the Dirichlet-multinomial and Connor–Mosimann distributions, the Neerchal–Morel distribution, the negative-multinomial distribution, certain distributions on partitions, and zero-truncated and zero-inflated distributions. These MM algorithms increase the likelihood at each iteration and reliably converge to the maximum from well-chosen initial values. Because they involve no matrix inversion, the algorithms are especially pertinent to high-dimensional problems. To illustrate the performance of the MM algorithms, we compare them to Newton’s method on data used to classify handwritten digits.     

Some Classes of Multivariate Life Distributions in Discrete Time

New classes of multivariate survival distribution functions based on monotonic behaviour of a multivariate failure rate are developed in the discrete set up. Relationship among the classes along with multivariate geometric distributions that act as boundaries of the various classes are identified.     

多元p-阶刘维尔分布:参数估计与假设检验(英语)

在观察服从p-阶刘维尔分布时,讨论了参数估计与假设检验问题。对密度生成子作某些假设后,得到了MLE,UMVU,UMP及UMPU,推广了独立同分布指数分布、Garnma分布、Weibull分布时的经典结果。     

On the Estimation of the Parameters of Multivariate Stable Distributions

In the paper, the asymptotic normality for a new estimator for the spectral measure of a multivariate stable distribution is proved. Also an estimator for the density of a multivariate stable distribution is proposed, its properties are investigated. The dependence of a stable density on exponent and the spectral measure is investigated.     

二元寿命分布的识别性及参数估计

讨论二元寿命分布的识别性及参数估计,仅是最小值的分布已知时,只有一个参数可识别,当可识最小值的分布已知时,所有参数皆可识别;由此得到了所有参数的最大似然估计.     

Bivariate Sarmanov Phase-Type Distributions for Joint Lifetimes Modeling

Methodology and Computing in Applied Probability - In this paper, we are interested in the dependence between lifetimes based on a joint survival model. This model is built using the bivariate...     

多元线性模型参数的部分压缩估计

考虑多元线性回归模型Y=XB ε,其中E(Vec(ε))=0,Cov(Vec(ε))=∑In,当设计阵X呈病态时,模型参数的LS估计不再是一个优良估计,为此,提出了一种部分压缩估计,并分析了其性质.     

具有相型服务分布的排队系统的性能灵敏度分析

具有非线数服务分布的排队网络已被广泛应用于许多领域,如通讯网络和管理系统。本文借助于无穷小说矩阵摄动方法,研究了M/PH/1排队系统的稳态性能灵敏度分析问题,给出了性能灵敏度公式,并表明了稳态性能灵敏度很容易通过系统势能进行计算。同时,给出一种计算势能及性能导数的算法。这个算法可直接用于系统的控制与优化,因为它基于分析系统的一条单一样本轨道。最后提供一个数值例子来表明这个算法的应用。     

定数截尾场合下混合指数威布尔分布的参数估计

混合指数威布尔分布是寿命数据分析中一个重要的统计模型.但是利用传统的矩法估计,极大似然估计等估计模型的参数比较困难.应用ECM算法,研究了混合指数威布尔分布在定数截尾数据场合下的参数估计问题,并以数值模拟验证用ECM算法来估计混合指数威布尔分布在定数截尾数据场合下的有效性.     

二元Freund型指数分布的特征及参数估计

利用分布密度分拆的思想,导出了二元Freund型指数分布的一个特征,利用该特征,获得了二元Freund型指数分布参数的最大似然估计及矩估计,还给出了强度服从二元Freund型指数分布时并联结构系统的可靠度估计及模拟.     

Multivariate Distributions from Mixtures of Max-Infinitely Divisible Distributions

A class of multivariate distributions that are mixtures of the positive powers of a max-infinitely divisible distribution are studied. A subclass has the property that all weighted minima or maxima belong to a given location or scale family. By choosing appropriate parametric families for the mixing distribution and the distribution being mixed, families of multivariate copulas with a flexible dependence structure and with closed form cumulative distribution functions are obtained. Some dependence properties of the class, as well as some characterizations, are given. Conditions for max-infinite divisibility of multivariate distributions are obtained.     

Discrete Tempered Stable Distributions

Methodology and Computing in Applied Probability - Discrete tempered stable distributions are a large and flexible class of models for heavy tailed and overdispersed count data. In this paper we...     

Mlinex损失函数下一类分布族参数的Bayes估计

考虑分布函数形如F(x;θ)=1-[g(x)]~θ或[1—g(x)]~θ,A≤x≤B,θ0的分布族,其中g(x)是关于x单调递减的可微函数,且g(A)=1,g(B)=0.在Mlinex损失函数下,给出了其中参数θ的Bayes估计及其容许性,并对分布的一个充分统计量的逆线性形式的容许性进行讨论.最后通过蒙特卡洛模拟说明Bayes估计在小样本情形时的优良表现.     

Stochastic Ordering of Multivariate Normal Distributions

We show an interesting identity for Ef(Y) – Ef(X), where X, Yare normally distributed random vectors and f is a function fulfilling some weak regularity condition. This identity will be used for a unified derivation of sufficient conditions for stochastic ordering results of multivariate normal distributions, some well known ones as well as some new ones. Moreover, we will show that many of these conditions are also necessary. As examples we will consider the usual stochastic order, convex order, upper orthant order, supermodular order and directionally convex order.     

Variational Inequalities for Arbitrary Multivariate Distributions

Upper bounds for the total variation distance between two arbitrary multivariate distributions are obtained in terms of the correspondingw-functions. The results extend some previous inequalities satisfied by the normal distribution. Some examples are also given.     

Estimation of the Scale Matrix and its Eigenvalues in the Wishart and the Multivariate F Distributions

In this paper, the problem of estimating the scale matrix and their eigenvalues in a Wishart distribution and in a multivariate F distribution (which arise naturally from a two-sample setting) are considered. A new class of estimators which shrink the eigenvalues towards their arithmetic mean are proposed. It is shown that the new estimator which dominates the usual unbiased estimator under the squared error loss function. A simulation study was carried out to study the performance of these estimators.     

Multivariate Exponential Distributions with Constant Failure Rates

In this paper a multivariate failure rate representation based on Cox's conditional failure rate is introduced, characterizations of the Freund–Block and the Marshall–Olkin multivariate exponential distributions are obtained, and generalizations of the Block–Basu and the Friday–Patil bivariate exponential distributions are proposed.     

Stability and Independence for Multivariate Refinable Distributions

Due to their so-called time-frequency localization properties, wavelets have become a powerful tool in signal analysis and image processing. Typical constructions of wavelets depend on the stability of the shifts of an underlying refinable function. In this paper, we derive necessary and sufficient conditions for the stability of the shifts of certain compactly supported refinable functions. These conditions are in terms of the zeros of the refinement mask. Our results are actually applicable to more general distributions which are not of function type, if we generalize the notion of stability appropriately. We also provide a similar characterization of the (global) linear independence of the shifts. We present several examples illustrating our results, as well as one example in which known results on box splines are derived using the theorems of this paper.