半参数回归模型拟极大似然估计的渐近分布

用拟极大似然估计方法研究了误差为AR(1)时间序列的半参数回归模型,得到了参数及非参数的拟极大似然估计量,并研究了它们的渐近分布.     

On Asymptotic Behavior for Singularities of the Powers of Mean Curvature Flow

Let M^n be a smooth, compact manifold without boundary, and F0 ： M^n→ R^n＋1 a smooth immersion which is convex. The one-parameter families F（·, t） ： M^n× [0, T） → R^n＋1 of hypersurfaces Mt^n= F（·,t）（M^n） satisfy an initial value problem dF/dt （·,t） = -H^k（· ,t）v（· ,t）, F（· ,0） = F0（· ）, where H is the mean curvature and u（·,t） is the outer unit normal at F（·, t）, such that -Hu = H is the mean curvature vector, and k 〉 0 is a constant. This problem is called H^k-fiow. Such flow will develop singularities after finite time. According to the blow-up rate of the square norm of the second fundamental forms, the authors analyze the structure of the rescaled limit by classifying the singularities as two types, i.e., Type Ⅰ and Type Ⅱ. It is proved that for Type Ⅰ singularity, the limiting hypersurface satisfies an elliptic equation; for Type Ⅱ singularity, the limiting hypersurface must be a translating soliton.     

On the Asymptotic Behavior of Distributions of First-Passage Times,II

In this paper, the asymptotic behavior of and estimates for the distribution of first-passage times for a random walk with nonzero drift are obtained in the case of passage of zero level (in both directions).     

On the Asymptotic Behavior of the Distributions of First-Passage Times, I

In this paper, the asymptotic behavior of and estimates for the distribution of first-passage times for a random walk are obtained in the cases of fixed and increasing levels. In the first part of the paper, the case of zero level is studied.     

Asymptotic Behavior of Sample Mean Direction for Spheres

In this note we consider some asymptotic properties of empirical mean direction on spheres. We do not require any symmetry for the underlying density. Thus our results provide the framework for an asymptotic inference regarding mean direction under very weak model assumptions. Mean direction is a specialization of the more general concept of mean location applicable to arbitrary (compact) submanifolds of Euclidean space, to which the methods of this paper could be applied.     

The Asymptotic Behavior of the Ruin Probability within a Random Horizon

Subject to the assumption that the common distribution of claim sizes belongs to the extendedregular variation class,the present work obtains a simple asymptotic formula for the ruin probability within arandom or nonrandom horizon in the renewal model.     

On the Rates of Asymptotic Normality for Bernstein Polynomial Estimators in a Triangular Array

Methodology and Computing in Applied Probability - It is well known that the empirical distribution function has superior properties as an estimator of the underlying distribution function F....     

�������ֲ���ƽ�����������޵����������о�

设备的平均寿命是可靠性研究中的的一个重要指标.对威布尔分布来说, 由于平均寿命没有明显的枢轴量,因此给出平均寿命的精确的置信限较为困难.本文分别利用广义枢轴量、WCF展开以及三阶法三种方法,得到了设备寿命服从威布尔分布时的平均寿命的(近似)置信下限.最后对上述三种方法分别进行了模拟比较,结果显示文中给出的方法对于中小样本情形下得到的平均寿命的置信限是比较精确的.     

常利息力下非标准连续时间更新风险模型破产概率的渐近性态

讨论一个非标准连续时间更新风险模型,其中理赔变量序列为一列两两尾拟渐近独立(TQAI)非负随机变量,在常数利息力假定下,得到了其有限时间破产概率的渐近估计式,并进一步讨论了估计的一致性,推广了[1,2,8]等文献的结果.     

积分第二中值定理“中间点”的渐近性再研究

继续研究积分第二中值定理,建立了其"中间点"渐近性的几个结果,他们可以认为是对刘文武,吴致友,夏雪等人结果的改进和推广.     

Asymptotic Behavior of Solutions of a Strongly Nonlinear Model of a Crystal Lattice

We consider a system of hyperbolic nonlinear equations describing the dynamics of interaction between optical and acoustic modes of a complex crystal lattice (without a symmetry center) consisting of two sublattices. This system can be considered a nonlinear generalization of the well-known Born-Huang Kun model to the case of arbitrarily large sublattice displacements. For a suitable choice of parameters, the system reduces to the sine-Gordon equation or to the classical equations of elasticity theory. If we introduce physically natural dissipative forces into the system, then we can prove that a compact attractor exists and that trajectories converge to equilibrium solutions. In the one-dimensional case, we describe the structure of equilibrium solutions completely and obtain asymptotic solutions for the wave propagation. In the presence of inhomogeneous perturbations, this system is reducible to the well-known Hopfield model describing the attractor neural network and having complex behavior regimes.__________Translated from Teoreticheskaya i Matematicheskaya Fizika, Vol. 143, No. 3, pp. 357–367, June, 2005.     

右删失混合相依模型下几种危险率函数估计的渐近性质

本文在右删失混合相依模型下,证明了密度函数和危险率函数的核类型估计具有与i.i.d.情形一样的渐近行为.并在极小平均平方误差准则下,得到了核危险率估计的最优窗宽为O(n-1/5).     

On Necessary and Sufficient Conditions for the Asymptotic Stability of Impulsive Systems

We prove that the sufficient conditions for the asymptotic stability of impulsive systems obtained by Gurgula and Perestyuk are also necessary conditions.     

分布函数尾端点估计量的渐近性质

当极值指标小于0时,本文给出了分布函数F(x)的尾端点估计量,证明了该估计量的强相合性和弱相合性;在二阶正规变化条件下,通过限制正规变化函数的收敛速度,给出了强收敛速度,证明了渐近正态性,进而可以构造F(x)的尾端点的渐近置信区间.     

不同分布的卷积的局部封闭性及局部渐近性的充分条件和必要条件

得到了支撑在[O,∞)上的不同分布的卷积(包括卷积根)的局部封闭性及局部渐近性的充分条件和必要条件,它揭示了不同分布的卷积及两两卷积之间的内在关系.这一结果的充分性部分推广了Geluk等非局部的相应结果,并且两者使用的方法是不同的;而这一结果的必要性部分是Geluk等人的结果中所没有的.最后,讨论了(-∞,∞)上不同分布卷积的局部封闭性及局部渐近性.     

On the Asymptotic Behavior of Mechanical Systems with Friction

Siberian Mathematical Journal - We study the asymptotic behavior of systems with the Coulomb friction expressed as Lagrange’s equations of the second kind with solutions in the sense of...     

Sparre Anderson模型中随机时破产概率的一致渐近性

随机时破产概率是有限时破产概率在时间上的随机化.本文研究了带折现的Sparre Anderson模型中随机时破产概率的一致渐近性.在一些假设条件下,最终得到一致渐近公式.     

Asymptotic Normality of the Minimum Non-Hilbertian Distance Estimators for a Diffusion Process with Small Noise

A one-dimensional diffusion type process with small noise is observed up to the time T. It depends on an unknown real parameter. Some minimum distance estimators of this parameter are considered. These estimators are defined using the L ^p-metric or the uniform metric. The limiting distribution of the normalizing minimum distance estimators (as the noise vanishing) is known to be the distribution of a random variable. The distribution of this random variable is studied as the time T goes to the infinity. We will prove under some conditions that it has a limiting Gaussian law. This revised version was published online in June 2006 with corrections to the Cover Date.