首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 78 毫秒
1.
对具有无穷方差的非线性自回归序列x_t=φ(x_(t-1),x_(t-2),…,x_(t-p),θ) ε_t,E(ε_t~2)=∞,利用局部二次近似和连续函数空间C(R~q)上弱收敛随机过程最小点的渐近性质,证明了若存在δ≥1,使得E|ε_t|~δ<∞成立,则θ满足一定条件的自加权L_1估计θ_(L_1)是渐近正态估计,Wald检验统计量也具有通常的x~2分布,为模型的统计推断提供了理论基础.  相似文献   

2.
近年来时间序列分析中的模型识别和参数估计方法(如[1—3]),得到了广泛的应用与发展。关于参数估计的渐近性理论研究,也随之被重视起来。所谓估计的渐近性,是指估计量随着样本长度不断增加时所具有的各种收敛性。很多文章(如[4—7])研究了滑动平均与自回归等模型参数估计的渐近性质。在这些文章中讨论了参数估计的依概率收  相似文献   

3.
本文考虑误差为自回归过程的固定效应面板数据部分线性回归模型的估计.对于固定效应短时间序列面板数据,通常使用的自回归误差结构拟合方法不能得到一个一致的自回归系数估计量.因此本文提出一个替代估计并证明所提出的自回归系数估计是一致的,且该方法在任何阶的自回归误差下都是可行的.进一步,通过结合B样条近似,截面最小二乘虚拟变量(LSDV)技术和自回归误差结构的一致估计,本文使用加权截面LSDV估计参数部分和加权B样条(BS)估计非参数部分,所得到的加权截面LSDV估计量被证明是渐近正态的,且比可忽略误差的自回归结构模型更渐近有效.另外,加权BS估计量被推导出具有渐近偏差和渐近正态性.模拟研究和实际例子相应地说明了所估计程序的有限样本性.  相似文献   

4.
本文对左截断模型, 利用局部多项式的方法构造了非参数回归函数的局部M 估计. 在观察样本为平稳α-混合序列下, 建立了该估计量的强弱相合性以及渐近正态性. 模拟研究显示回归函数的局部M 估计比Nadaraya-Watson 型估计和局部多项式估计更稳健.  相似文献   

5.
随机删失数据非线性回归模型的最小一乘估计   总被引:5,自引:0,他引:5       下载免费PDF全文
研究了随机删失数据非线性回归模型的最小一乘(LAD)估计问题, 证明了LAD估计量的渐近性质, 包括相合性、依概率有界性和渐近正态性等. 模拟结果显示对删失数据回归问题, LAD估计仍比最小二乘估计(LSE)稳健.  相似文献   

6.
对于线性回归模型,在因变量受到另一与之独立的随机变量序列的污染时,基于最小一乘的方法给出模型参数的估计.在一定条件下,证明了估计量的相合性和渐近正态性,并使用模拟对估计方法的小样本性质进行了分析.模拟结果显示,本文所提方法在小样本情况下表现良好.  相似文献   

7.
φ-混合样本下,当响应变量满足随机缺失机制时,利用回归填补方法填补缺失的数据,在此基础上给出了线性模型回归系数的估计,并在一定的条件下证明了估计的渐近正态性.  相似文献   

8.
分位数自回归模型作为一类常用的变系数时间序列模型,在理论研究和实际问题中都有广泛的应用.考虑到这类模型具有自回归的结构属性,数据采集过程中产生的额外信息,以相依辅助信息函数的形式被引入到模型系数的估计中来.该文应用经验似然方法得到了模型系数的估计量,得到了模型系数的估计量,并论证了其渐近正态性.基于渐近正态性的理论结果,进一步讨论了模型系数线性约束性问题的Wald检验统计量的渐近性质.数值模拟和实例数据分析的结果均表明,利用经验似然估计处理带相依辅助信息函数的方法较传统的分位数回归估计更有效.因而,一般常系数线性分位数回归模型在独立假设下的结果,被推广至具有相依结构的一类变系数模型中去.  相似文献   

9.
冯海林  罗倩倩 《应用数学》2020,33(1):209-218
左截断数据是一类具有特殊结构的缺失数据,当且仅当研究变量大于一定的阈值时才能取得观察值.本文针对左截断数据下的非线性回归模型,提出了加权分位数估计方法,利用加权方式处理左截断缺失数据,取得了与完整数据相近的估计结果.并在一定假设条件下,证明了所提估计方法的一致性和渐近正态性等大样本性质,最后通过数值模拟展现所提估计方法的有限样本表现.  相似文献   

10.
考虑线性回归模型y_i=x_i~Tβ_0+e_i,i=1,2,…,n,其中误差{e_i,i=1,2,...,n}为渐近几乎负相关的随机序列.研究了该模型中参数的M估计的强相合性,也得到了AANA序列的Bernstein型不等式,推广了NA样本的相应结论.  相似文献   

11.
In this paper, we introduce a new measure of asymmetry, called log-Minkowski measure of asymmetry for planar convex bodies in terms of the \(L_0\)-mixed volume, and show that triangles are the most asymmetric planar convex bodies in the sense of this measure of asymmetry.  相似文献   

12.
Li  Qian  Bai  Yanqin  Yu  Changjun  Yuan  Ya-xiang 《中国科学 数学(英文版)》2019,62(1):185-204
In this paper, we consider the problem of finding sparse solutions for underdetermined systems of linear equations, which can be formulated as a class of L_0 norm minimization problem. By using the least absolute residual approximation, we propose a new piecewis, quadratic function to approximate the L_0 norm.Then, we develop a piecewise quadratic approximation(PQA) model where the objective function is given by the summation of a smooth non-convex component and a non-smooth convex component. To solve the(PQA) model,we present an algorithm based on the idea of the iterative thresholding algorithm and derive the convergence and the convergence rate. Finally, we carry out a series of numerical experiments to demonstrate the performance of the proposed algorithm for(PQA). We also conduct a phase diagram analysis to further show the superiority of(PQA) over L_1 and L_(1/2) regularizations.  相似文献   

13.
均匀性度量是构作均匀设计的基础,本文从距离概念出发,通过对称的方法,得到一种新的距离函数-势函数,并将势函数作为衡量任意凸多面体上布点均匀性好坏的准则.数值例子和多变量Kendall 协和系数检验表明,当试验区域限制在单位立方体上时,势函数与目前常用的两种偏差-中心化L_2-偏差和可卷L_2.偏差在度量布点均匀性方面结论一致.  相似文献   

14.
In this paper, the periodic boundary problem and the initial value problem for the nonlinear system of parabolic type $\[{u_t} = (grad\varphi (u))\]$ are studied, where $\[u = ({u_1}, \cdots ,{u_N})\]$ is an N-dimensional vector valued function, $\[\varphi (u)\]$ is a strict convex function of vector variable $\[u\]$, and its matrix of derivatives of second order is zero-definite at $\[u = 0\]$. This system is degenerate. The definition of the generalized solution of the problem: $\[u(x,t) \in {L_\infty }((0,T);{L_2}(R)),\]$, grad $\[\varphi (u) \in {L_\infty }((0,T);W_2^{(1)}(R)),\]$ and it satisfies appropriate integral relation. The existence and uniqueness of the generalized solution of the problem are proved. When N=1, the system is the commonly so-called degenerate partial differential equation of filtration type.  相似文献   

15.
Recently Auslender & Crouzeix introduced a well-behaved asymptotical notion for convex functions. The aim of this work is to extend this notion to the saddle case  相似文献   

16.
The two major ways of obtaining fundamental domains for discrete subgroups of SL(2,?) are the Dirichlet Polygon construction (see Lehner in Discontinuous Groups and Automorphic Functions, American Mathematical Society, Providence, 1964) and Ford’s construction (see Ford in Automorphic Functions, McGraw–Hill, New York, 1929). Each of these two methods yield a hyperbolically convex fundamental domain for any discrete subgroup of SL(2,?).However, the Dirichlet polygon construction and Ford’s construction are not well adapted for the actual construction of a hyperbolically convex fundamental domain due to their nature of construction and their reliance on knowing almost all elements of the group under discussion.
A third-and most important and practical-method of obtaining a fundamental domain is through the use of a right coset decomposition as described below. Let Γ2 be a subgroup of Γ1 and
$\Gamma_{1}=\Gamma_{2}\cdot \{L_{1},L_{2},\ldots,L_{m}\}.$
If \(\mathbb{F}\) is a fundamental domain of the bigger group Γ1, then the set
$\mathcal{R}_{\Gamma}=\Biggl(\overline{\bigcup_{k=1}^{m}L_{k}(\mathbb{F})}\,\Biggr)^{o}$
(1)
is a fundamental domain of Γ2. One can ask at this juncture, is it possible to choose the right cosets suitably so that the set ?Γ is hyperbolically convex? We will answer this question affirmatively for
$\Gamma_{1}=\Gamma(1)\quad \mbox{and}\quad \mathbb{F}=\biggl\{\tau \in \mathbb{H}:|\tau|>1\ \&;\ |\mathrm{Re}(\tau)|<\frac{1}{2}\biggr\}.$
  相似文献   

17.
The alternating direction method of multipliers (ADMM) is a benchmark for solving a two-block linearly constrained convex minimization model whose objective function is the sum of two functions without coupled variables. Meanwhile, it is known that the convergence is not guaranteed if the ADMM is directly extended to a multiple-block convex minimization model whose objective function has more than two functions. Recently, some authors have actively studied the strong convexity condition on the objective function to sufficiently ensure the convergence of the direct extension of ADMM or the resulting convergence when the original scheme is appropriately twisted. We focus on the three-block case of such a model whose objective function is the sum of three functions, and discuss the convergence of the direct extension of ADMM. We show that when one function in the objective is strongly convex, the penalty parameter and the operators in the linear equality constraint are appropriately restricted, it is sufficient to guarantee the convergence of the direct extension of ADMM. We further estimate the worst-case convergence rate measured by the iteration complexity in both the ergodic and nonergodic senses, and derive the globally linear convergence in asymptotical sense under some additional conditions.  相似文献   

18.
We present several conditions for generic uniqueness of tensor decompositions of multilinear rank \((1,\ L_{1},\ L_{1}),\cdots ,(1,\ L_{R},\ L_{R})\) terms. In geometric language, we prove that the joins of relevant subspace varieties are not tangentially weakly defective. We also give conditions for partial uniqueness of block term tensor decompositions by proving that the joins of relevant subspace varieties are not defective.  相似文献   

19.
In this paper, new necessary conditions for Pareto minimal points to sets and Pareto minimizers for constrained multiobjective optimization problems are established without the sequentially normal compactness property and the asymptotical compactness condition imposed on closed and convex ordering cones in Bao and Mordukhovich [10] and Durea and Dutta [5], respectively. Our approach is based on a version of the separation theorem for nonconvex sets and the subdifferentials of vector-valued and set-valued mappings. Furthermore, applications in mathematical finance and approximation theory are discussed.  相似文献   

20.
In this paper, a new class of complex-valued projective neural network is introduced and studied on a nonempty, closed, and convex subset of a finite-dimensional complex space. An existence and uniqueness result for the equilibrium point of complex-valued projective neural network is proved under some suitable conditions. Moreover, by utilizing the linear matrix inequality technique, some sufficient conditions are presented to ensure the asymptotical stability of the complex-valued projective neural network. Finally, two examples are given to illustrate the validity and feasibility of main results.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号