误差非线性回归模型基于几何方法的若干二阶渐近性质

该文用微分几何方法对AR(q)误差非线性回归模型若干二 阶渐近性质进行了研究. 作者基于Fisher信息阵在欧氏空间定义了内积，并在期望参数空间建立了几何结构. 基于上述几何结构，给出了AR(q)误差非线性回归模型若干二阶渐近性质的曲率表示. 将前人的一些结果推广到AR(q)误差非线性回归模型.      

NSD序列加权和的中心极限定理及其在EV回归模型中的应用

基于负超可加相依(简称为NSD)随机序列的性质及其一些不等式,利用随机变量的截断方法建立了NSD随机序列加权和的中心极限定理,从而推广了负相协NA随机序列的相应结论.并将其应用到变系数EV回归模型,得到了未知参数LS估计的渐近正态性.     

NA序列广义Jamison型加权和的几乎处处收敛性

本文从随机变量序列广义Ｊａｍｉｓｏｎ型加权和的一个系数指标函数自身性质出发，讨论了广义Ｊａｍｉｓｏｎ型加权和的强稳定性，避免了控制函数的引入， 进一步还得到了更一般的ＮＡ序列广义Ｊａｍｉｓｏｎ型加权和的几乎处处收敛的条件，并将前人的若干结论包含为特例．     

基于Bootstrap的厚尾相依序列持久性变点检验

基于修正方差比率函数给出一种检验厚尾序列持久性变点的统计量.在无变点的假设下得到了统计量的渐近分布.为避免检验渐近分布中的厚尾指数,构造Bootstrap抽样方法来确定渐近分布的经验临界值.数值模拟研究结果说明修正方差比率统计量及Bootstrap抽样方法的有效性.     

线型优化最大熵线性预测方法自回归模型三种求解方法的比较

采用三种方法：修正协方差法MCOV(Modified Covariance Method)、递推极大似然估计法RMLE(Recursive Maximum Likelihood Estimator)和伯格法(Burg Method)求解线型优化最大熵线性预测方法中的自回归模型系数,并且在不同求解方法情况下,将阶次、信噪比对光谱复原的影响作了详尽的比较.研究结果表明:在线型优化最大熵线性预测方法的自回归模型系数三种求解方法中,修正协方差法要优于递推极大似然估计法和伯格法.     

Limit Theorems for the Maximum Terms of a Sequence of Random Variables with Marginal Geometric Distributions

Let X _n1 ^* , ... X _nn ^* be a sequence of n independent random variables which have a geometric distribution with the parameter p _n = 1/n, and M _n ^* = \max\{X _n1 ^* , ... X _nn ^* }. Let Z ₁, Z₂, Z₃, ... be a sequence of independent random variables with the uniform distribution over the set N _n = {1, 2, ... n}. For each j N _n let us denote X _nj = min{k : Z_k = j}, M _n = max{X_n1, ... X_nn}, and let S _n be the 2nd largest among X _n1, X_n2, ... X_nn. Using the methodology of verifying D(u_n) and D'(u_n) mixing conditions we prove herein that the maximum M _n has the same type I limiting distribution as the maximum M _n ^* and estimate the rate of convergence. The limiting bivariate distribution of (S_n, M_n) is also obtained. Let _n, _n N_n, , and T _n = min{M(A_n), M(B_n)}. We determine herein the limiting distribution of random variable T _n in the case _n , _n/_n > 0, as n .     

Compound Poisson Approximation of the Number of Exceedances in Gaussian Sequences

Consider a finite sequence of Gaussian random variables. Count the number of exceedances of some level a, i.e. the number of values exceeding the level. Let this level and the length of the sequence increase simultaneously so that the expected number of exceedances remains fixed. It is well-known that if the long-range dependence is not too strong, the number of exceeding points converges in distribution to a Poisson distribution. However, for sequences with some individual large correlations, the Poisson convergence is slow due to clumping. Using Steins method we show that, at least for m-dependent sequences, the rate of convergence is improved by using compound Poisson as approximating distribution. An explicit bound for the convergence rate is derived for the compound Poisson approximation, and also for a subclass of the compound Poisson distribution, where only clumps of size two are considered. Results from numerical calculations and simulations are also presented.     

小波包分解及其参数模型

本文在小波包分析的基础之上，实现了适合于一维信号分析的小波分解算法，并将小波包分析理论和参数模型有机地结合了起来，构造了小波包参数模型。     

Extended well-posedness of optimization problems

The well-posedness concept introduced in Ref. 1 for global optimization problems with a unique solution is generalized here to problems with many minimizers, under the name of extended well-posedness. It is shown that this new property can be characterized by metric criteria, which parallel to some extent those known about generalized Tikhonov well-posedness.This work was partially supported by MURST, Fondi 40%, Rome, Italy.     

A Feigenbaum sequence of bifurcations in the Lorenz model

For some high values of the Rayleigh numberr, the Lorenz model exhibits laminar behavior due to the presence of a stable periodic orbit. A detailed numerical study shows that, forr decreasing, the turbulent behavior is reached via an infinite sequence of bifurcations, whereas forr increasing, this is due to a collapse of the stable orbit to a hyperbolic one. The infinite sequence of bifurcations is found to be compatible with Feigenbaum's conjecture.