线性模型参数的聚集改进广义Liu估计的相对效率

对于聚集数据的线性模型,给出了参数β的聚集改进广义Liu估计,研究了该估计相对于最小二乘估计及相对于Peter—Karsten估计的两种相对效率,并得到了相对效率的上界.实例分析表明,聚集改进广义Liu估计比最小二乘估计、Peter—Karsten估计更有效.     

指数分布串—并联混合系统产品的统计分析

给出单元寿命服从同一指数分布的串-并联混合系统产品参数的矩估计和极大似然估计,并通过大量Monte-Carlo模拟比较了估计的精度,得到在样本容量小于35时矩估计优于极大似然估计,而样本容量不小于35时极大似然估计优于矩估计.另外,还给出了参数的精确区间估计与近似区间估计,并通过大量Monte-Carlo模拟考察了区间估计的精度.     

Haezendonck-Goovaerts资金分配的估计

本文用估计方程方法解决Haezendonck-Goovaerts资金分配的非参数估计问题,得到Haezendonck-Goovaerts资金分配的经验估计、估计方程估计以及各自的大样本性质,数值模拟分析了样本容量对Haezendonck-Goovaerts资金分配估计的影响。     

Panel模型中常见估计的比较

本文研究了Panel模型中回归系数常见估计的比较问题,给出了在Pitman准则,协方差阵准则和广义均方误差准则下最小二乘估计,Within估计,Between估计及两步估计之间的优良性比较结果.特别地,本文证明了在Pitman准则下最小二乘估计一致地优于Between估计.     

不同自变量的变系数模型的估计

讨论具有不同自变量的变系数模型的函数系数的估计及其大样本性质。使用局部线性方法和积分方法,得到函数系数的积分估计;由于该估计有较大的方差,进一步使用回切法改进这一估计,获得了函数系数的改进估计;同时,研究了改进估计的渐近正态性。最后,用模拟例子说明提出的估计方法是有效的。     

关于无偏估计的若干问题

通过理论分析和实例讨论有关无偏估计的若干问题：无偏估计不一定存在;无偏估计一般不唯一;在均方误差意义下,无偏估计不一定优于有偏估计;均方误差最小的估计是最小方差无偏估计,但反之不然。     

帕累托索赔分布中风险参数的经验贝叶斯估计

本文建立了贝叶斯模型,讨论了帕累托索赔额分布中参数的估计问题,得到了风险参数的极大似然估计、贝叶斯估计和信度估计,并证明了这些估计的强相合性.在均方误差的意义下比较了这些估计的好坏,并通过数值模拟对均方误差进行了验证,结果表明,贝叶斯估计比其他估计具有较小的均方误差.最后,给出了结构参数的估计并证明了经验贝叶斯估计和经验贝叶斯信度估计的渐近最优性.     

平衡随机模型中方差分量的非负估计

众所周知, 对于平衡随机模型, 方差分量的方差分析估计为一致最小方差无偏估计. 本文基于方差分量的方差分析估计, 构造了一个二次不变估计类, 它包含了一些常用重要估计. 证明了该估计类在一定条件下在均方误差意义下一致优于方差分析估计, 并在此估计类基础上, 给出了方差分量的两种非负估计, 它们在均方误差意义下分别一致优于方差分析估计和限制极大似然估计, 且有显式解、容易计算.     

相依数据部分线性模型的M估计的收敛速度

讨论了相依数据部分线性模型的M估计的收敛速度问题,在一定条件下,证明了参数分量的M估计具有渐进正态性,非参量分量的回归B样条M估计达到非参数回归的最优全局收敛速度,这里的理论结果包括最小一乘估计、最小二乘估计、Huber M估计及L_p模估计作为特例.     

基于价格极值构建有效价差的广义矩估计

基于Corwin和Schultz(2012)提出的有效价差的High-Low估计,结合价格极值信息得到新的一阶矩条件,构造了有效价差的广义矩估计。随后通过随机数值模拟比较了基于价格极值的广义矩估计(GMM)与Roll的协方差估计、Bayes估计以及Corwin和Schultz的High-Low估计在多种不同状态下的估计精度。数值模拟结果显示,无论在交易连续的理想状态下还是交易不连续且波动率相对不高的非理想状态下,GMM估计的精度均高于其余三种估计;基于我国股票市场的实例分析,也表明GMM估计的估计精度优于其余三种估计。因此,GMM估计为度量金融资产的交易成本提供了一种有效方法。     

On a Mathematical Comparison between Hierarchy and Network with a Classification of Coordination Structures

This paper proposes a mathematical model to compare a network organization with a hierarchical organization. In order to formulate the model, we define a three-dimensional framework of the coordination structure of a network and of other typical coordination structures. In the framework, we can define a network structure by contrasting it with a hierarchy, in terms of the distribution of decision making, which is one of the main features of information processing. Based on this definition, we have developed a mathematical model for evaluating coordination structures. Using this model, we can derive two boundary conditions among the coordination structures with respect to the optimal coordination structure. The boundary conditions help us to understand why an organization changes its coordination structure from a hierarchy to a network and what factors cause this change. They enable us, for example, to find points of structural change where the optimal coordination structure shifts from a hierarchy to a hierarchy with delegation or from a hierarchy with delegation to a network, when the nature of the task changes from routine to non-routine. In conclusion, our framework and model may provide a basis for discussing the processes that occur when coordination structures change between a hierarchy and a network.     

年龄点t0之后的NBU性的非参数检验方法

NBU＊t0寿命分布中新元件的寿命随机地大于旧的年龄不小于t0的元件的剩余寿命,这为更广泛地模拟元件的老化和劣化现象提供了丰富的内容。本文首先对那些t0年龄点之后剩余寿命随机等于新元件寿命的元件的结构加以刻画,然后建立了一个非参数检验方法以区分这种随机等价性和t0年龄点后的严格的NBU性,并给出了针对一个NBU＊t0但非NBU的寿命分布的例子的数值模拟结果。     

The Ricci flow in a class of solvmanifolds

In this paper, we study the Ricci flow of solvmanifolds whose Lie algebra has an abelian ideal of codimension one, by using the bracket flow. We prove that solutions to the Ricci flow are immortal, the ω-limit of bracket flow solutions is a single point, and that for any sequence of times there exists a subsequence in which the Ricci flow converges, in the pointed topology, to a manifold which is locally isometric to a flat manifold. We give a functional which is non-increasing along a normalized bracket flow that will allow us to prove that given a sequence of times, one can extract a subsequence converging to an algebraic soliton, and to determine which of these limits are flat. Finally, we use these results to prove that if a Lie group in this class admits a Riemannian metric of negative sectional curvature, then the curvature of any Ricci flow solution will become negative in finite time.     

Koszul Bicomplexes and Generalized Koszul Complexes in Projective Dimension One

We describe Koszul type complexes associated with a linear map from any module to a free module, and vice versa with a linear map from a free module to an arbitrary module, generalizing the classical Koszul complexes. Given a short complex of finite free modules, we assemble these complexes to what we call Koszul bicomplexes. They are used in order to investigate the homology of the Koszul complexes in projective dimension one. As in the case of the classical Koszul complexes, this homology turns out to be grade sensitive. In a special setup, we obtain necessary conditions for a map of free modules to be lengthened to a short complex of free modules.     

Method of successive projections for finding a common point of sets in metric spaces

Many problems in applied mathematics can be abstracted into finding a common point of a finite collection of sets. If all the sets are closed and convex in a Hilbert space, the method of successive projections (MOSP) has been shown to converge to a solution point, i.e., a point in the intersection of the sets. These assumptions are however not suitable for a broad class of problems. In this paper, we generalize the MOSP to collections of approximately compact sets in metric spaces. We first define a sequence of successive projections (SOSP) in such a context and then proceed to establish conditions for the convergence of a SOSP to a solution point. Finally, we demonstrate an application of the method to digital signal restoration.     

Nearest-neighbour modelling of reciprocal chains

This paper focuses on the class of finite-state, discrete-index, reciprocal processes (reciprocal chains). Such a class of processes seems to be a suitable setup in many applications and, in particular, it appears well-suited for image-processing. While addressing this issue, the aim is 2-fold: theoretic and practical. As to the theoretic purpose, some new results are provided: first, a general stochastic realization result is provided for reciprocal chains endowed with a known, arbitrary, distribution. Such a model has the form of a fixed-degree, nearest-neighbour polynomial model. Next, the polynomial model is shown to be exactly linearizable, which means it is equivalent to a nearest-neighbour linear model in a different set of variables. The latter model turns out to be formally identical to the Levi–Frezza–Krener linear model of a Gaussian reciprocal process, although actually non-linear with respect to the chain's values. As far as the practical purpose is concerned, in order to yield an example of application an estimation issue is addressed: a suboptimal (polynomial-optimal) solution is derived for the smoothing problem of a reciprocal chain partially observed under non-Gaussian noise. To this purpose, two kinds of boundary conditions (Dirichlet and Cyclic), specifying the reciprocal chain on a finite interval, are considered, and in both cases the model is shown to be well-posed, in a ‘wide-sense’. Under this view, some well-known representation results about Gaussian reciprocal processes extend, in a sense, to a ‘non-Gaussian’ case.     

Transverse curves and chain curvature in the Heisenberg group

A chain is the intersection of a complex totally geodesic subspace in complex hyperbolic 2-space with the boundary. The boundary admits a canonical contact structure, and chains are distiguished curves transverse to this structure. The space of chains is analyzed both as a quotient of the contact bundle, and as a subset of ℂP². The space of chains admits a canonical, indefinite Hermitian metric, and curves in the space of chains with null tangent vectors are shown to correspond to a path of chains tangent to a curve in the boundary transverse to the contact structure. A family of local differential chain curvature operators are introduced which exactly characterize when a transverse curve is a chain. In particular, operators that are invariant under the stabilizer of a point in the interior of complex hyperbolic space, or a point on the boundary, are developed in detail. Finally, these chain curvature operators are used to prove a generalization of Louiville's theorem: a sufficiently smooth mapping from the boundary of complex hyperbolic 2-space to itself which preserves chains must be the restriction of a global automorphism.     

A parametric GP model dealing with incomplete information for group decision-making

We consider a group decision-making problem where preferences given by the experts are articulated into the form of pairwise comparison matrices. In many cases, experts are not able to efficiently provide their preferences on some aspects of the problem because of a large number of alternatives, limited expertise related to some problem domain, unavailable data, etc., resulting in incomplete pairwise comparison matrices. Our goal is to develop a computational method to retrieve a group priority vector of the considered alternatives dealing with incomplete information. For that purpose, we have established an optimization problem in which a similarity function and a parametric compromise function are defined. Associated to this problem, a logarithmic goal programming formulation is considered to provide an effective procedure to compute the solution. Moreover, the parameters involved in the method have a clear meaning in the context of group problems.     

Solution to the variation problem for information path functional of a controlled random process

The paper introduces a new approach to dynamic modeling, using the variation principle, applied to a functional on trajectories of a controlled random process, and its connection to the process' information functional. In [V.S. Lerner, Dynamic approximation of a random information functional, J. Math. Anal. Appl. 327 (1) (2007) 494-514, available online 5-24-06], we presented the information path functional with the Lagrangian, determined by the parameters of a controlled stochastic equation. In this paper, the solution to the path functional's variation problem provides both a dynamic model of a random process and the model's optimal control, which allows us to build a two-level information model with a random process at the microlevel and a dynamic process at the macrolevel. A wide class of random objects, modeled by the Markov diffusion process and a common structure of the process' information functional, leads to a universal information structure of the dynamic model, which is specified and identified on a particular object with the applied optimal control functions. The developed mathematical formalism, based on classical methods, is aimed toward the solution of problems identification, combined with an optimal control synthesis, which is practically implemented and also demonstrated in the paper's example.     

A sufficient condition and a necessary condition for the diffusion approximations of multiclass queueing networks under priority service disciplines

We establish a sufficient condition for the existence of the (conventional) diffusion approximation for multiclass queueing networks under priority service disciplines. The sufficient condition relates to a sufficient condition for the weak stability of the fluid networks that correspond to the queueing networks under consideration. In addition, we establish a necessary condition for the network to have a continuous diffusion limit; the necessary condition is to require a reflection matrix (of dimension equal to the number of stations) to be completely-S. When applied to some examples, including generalized Jackson networks, single station multiclass queues, first-buffer-first-served re-entrant lines, a two-station Dai–Wang network and a three-station Dumas network, the sufficient condition coincides with the necessary condition.