二参数指数型有限混合分布

本文给出二参数指数型有限混合分布的带约束的极大似然估计的强相合性。     

重尾数据的混合Erlang分布拟合方法

PH分布具有良好的解析性质,重尾数据的PH近似是随机模型分析中的重要课题.混合Erlang分布是一种常见的PH分布,本文利用EM方法给出了重尾数据的混合Erlang分布拟合算法,通过Matlab软件对两类常见重尾数据进行实验,结果令人满意.最后,文章对混合Erlang分布拟合算法的进一步改进做了总结.     

两个未知均值方差混合模型有限制下对数极大似然比的极限分布

本文讨论了检验样本是来自一个正态总体还是两个未知均值和方差的正态的混合分布,采用对数极大似然比的检验,如果不加限制,Ｈａｒｔｉｎｇａｎｍ曾指出不是寻找的、Ｘ＾２分布,我们在混合的中了一点后得到了其极限分布产工给出了分位点数值表。     

多重星体的L_p-对偶混合几何表面积及其相关不等式

叶德平等人介绍了任意实数p(p≠-n)的多重凸体的L_p-混合几何表面积.本文给出了关于任意实数p(p≠n)的多重星体的L_p-对偶混合几何表面积的概念,并且建立了一些相关不等式.     

有限混合模型有限制Log极大似然比统计量的极限分布

有限混合模型的Log极大似然比统计量极限分布不是平常x2分布,1985年已为Hartigan指出.在这篇文章我们限制了混合比大于一正数下,讨论了两个含单个未知参数混合模型的Log极大似然比统计量的极限分布,它是零与x2分布的混合分布.     

指数类混合型索赔次数的分布及其应用

基于保险索赔的实际应用背景, 本文引出了一类指数类混合型索赔次数的分布并研究了其散度(dispersion)性质, 这类分布由复合Poisson-Geometric分布与指数类分布混合而得到. 本文给出了拟合这类分布的矩估计方法及我国汽车保险索赔数据的应用实例, 并给出了相应的检验结果.     

Gamma分布与Beta分布的一致渐近正态性

考虑了Gamma分布与Beta分布的一致渐近正态性.     

二元极值混合模型相关结构的研究

二元极值混合模型由于不能反映极值变量之间的完全相关性,因而在应用上受到了一定的限制,但对适当的相关性仍是一个很好的模型.本文给出了二元极值混合模型的一些基本性质,特别用随机模拟方法研究了对来自其它不同极值copula的随机样本,用混合模型拟合可能产生的影响. 结果表明,如果以Kendallτ表示变量间的相关性,在一定范围内,混合模型能够很好的反映其它模型所具有的相关性,且对渐近独立模型边际参数估计的偏差也不太大.最后应用混合条件分布与GEV条件分布分析英镑对美元和英镑对加元两支汇率日对数回报收益率的风险相关性.     

关于混合泊松分布之Willmot递推式的一个拓广

混合泊松分布的计算复杂与否视其结构分布而定.文章给出了结构分布密度函数满足一类一阶线性微分方程的混合泊松分布计算的递推式,它是Willmot递推式的一个拓广.     

双定数混合截尾下两参数Pareto分布的统计分析

在传统的定时和定数截尾试验的基础上,该文首次提出了一种新的截尾试验方案:双定数混合截尾.基于这类截尾数据求出了两参数Pareto分布参数的极大似然估计及θ的置信区间.当α已知时,取Gamma先验分布的情况下,求出了三种不同损失函数下参数θ、可靠度函数以及失效率函数的Bayes估计;当α,θ都未知时,分别取无信息先验分布...     

EXPLICIT EXPRESSIONS FOR SOME DISTRIBUTIONS RELATED TO RUIN PROBLEMS

The classical risk process that is perturbed by diffusion is studied .The explicit expressions for the runi probability and the surplus distribution of the risk process at the time of runi are obtained when the claim amount distribution is a finite mixture of exponential distributions of a Gamma (2,α） distribution.     

Moment-Based Approximations of Distributions Using Mixtures: Theory and Applications

There are a number of cases where the moments of a distribution are easily obtained, but theoretical distributions are not available in closed form. This paper shows how to use moment methods to approximate a theoretical univariate distribution with mixtures of known distributions. The methods are illustrated with gamma mixtures. It is shown that for a certain class of mixture distributions, which include the normal and gamma mixture families, one can solve for a p-point mixing distribution such that the corresponding mixture has exactly the same first 2p moments as the targeted univariate distribution. The gamma mixture approximation to the distribution of a positive weighted sums of independent central ² variables is demonstrated and compared with a number of existing approximations. The numerical results show that the new approximation is generally superior to these alternatives.     

S‐inequality for certain product measures

In this paper we prove the S‐inequality for certain product probability measures and ideals in . As a result, for the Weibull and Gamma product distributions we derive concentration of measure type estimates as well as optimal comparison of moments.     

Conservatism of the z Confidence Interval Under Symmetric and Asymmetric Departures from Normality

The robustness of the z-interval under nonnormality is investigated by finding its infimum coverage probability over suitably chosen broad class of distributions. In the case of n = 1, the infimum coverage probabilities over the normal scale mixture and the symmetric unimodal families of distributions are obtained analytically. For general n, the infimum problem is theoretically reduced to a finite dimensional minimization which is then obtained numerically. The obtained minimum coverage probabilities are very close to the nominal probabilities. These exact minimum coverage probabilities are often notably sharper than the lower bounds given by the Camp-Meidell-Gauss inequality. The family of general unimodal distributions is considered next to investigate the possible effect of asymmetry. The obtained infimum coverage probabilities over this family are found to be the same as the ones over the symmetric unimodal class.     

Approximation with generalized hyperexponential distributions: Weak convergence results

Generalized hyperexponential (GH) distributions are linear combinations of exponential CDFs with mixing parameters (positive and negative) that sum to unity. The denseness of the class GH with respect to the class of all CDFs defined on [0, ) is established by showing that a GH distribution can be found that is as close to a given CDF as desired, with respect to a suitably defined metric. The metric induces the usual topology of weak convergence so that, equivalently, there exists a sequence of GH CDFs that converges weakly to a given CDF. This result is established by using a similar result for weak convergence of Erlang mixtures. Various set inclusion relations are also obtained relating the GH distributions to other commonly used classes of approximating distributions, including generalized Erlang (GE), mixed generalized Erlang (MGE), those with reciprocal polynomial Laplace transforms (K _n ), those with rational Laplace transforms (R _n ), and phase-type (PH) distributions. A brief survey of the history and use of approximating distributions in queueing theory is also included.This research was partially supported by the Office of Naval Research under Contract No. N00014-86-K0029. Much of this work is taken from the first-named author's doctoral dissertation, accepted by the faculty at the University of Virginia.     

On estimating of the number of constituents of a finite mixture of continuous distributions

Summary Suppose thatH is a mixture of distributions for a given familyF A necessary and sufficient condition is obtained under whichH is, in fact, a finite mixture. An estimator of the number of distributions constituting the mixture is proposed assuming that the mixture is finite and its asymptotic properties are investigated.     

Failure rate of the inverse Gaussian-Weibull mixture model

Motivated by the idea that different causes of failure of a given system could lead to different failure distributions, a mixture of two-component distributions, one of which is the two-parameter Inverse Gaussian (IG) and the other the two-parameter Weibull (W), is proposed as a failure model. The IG-W mixture model convers several types of failure rates (FR's). It is shown that depending on the parameter values, the IG-W mixture model is capable of covering six different combinations of FR's, as one of the components has an upsidedown bathtub failure rate (UBTFR) or increasing failure rate (IFR) and the other component has a decreasing failure rate (DFR), constant failure rate (CFR), or IFR. A study is made for the mixed FR based on these six combinations.     

双边定数截尾下Pareto分布的可靠性分析

基于双边定数截尾样本,选取未知参数的先验分布为无信息先验和Gamma分布,分别在平方损失和LINEX损失下,研究了Pareto分布的形状参数和可靠性指标(可靠度和失效率)的Bayes估计.为了研究估计的精度,采用Monte-Carlo模拟的方法给出了数值检验的例子.结果表明在LINEX损失下并选用Gamma先验分布时,参数的Bayes估计是最优的.     

正态分布和瑞利分布混合情形下的参数估计及分类问题

学者往往用单一的分布模拟和拟合杂波,如正态分布、瑞利分布和威布尔分布等。然而在实际中,雷达杂波由多种类型的杂波组成,单一分布通常不能精确刻画雷达杂波规律,因此,应用混合分布模型对雷达杂波数据建模更准确。本文考虑用正态分布和瑞利分布的混合分布拟合杂波,并应用矩估计方法和基于EM算法的极大似然估计方法估计模型参数,最后,应用最大后验概率分类准则验证2种估计方法的分类准确率。通过数据模拟,得出极大似然估计的效果和分类准确率都要优于矩估计的估计效果和分类准确率。