序约束下AR(p)-ARCH(q)模型参数的估计与检验

In this paper, we study a stationary AR(p)-ARCH(q) model with parameter vectors a and β. We propose a method for computing the maximum likelihood estimator (MLE) of parameters under the nonnegative restriction. A similar method is also proposed for the case that the parameters are restricted by a simple order: α1≥α2≥…≥αq, andβ1≥β2≥…βp. The strong consistency of the above two estimators is discussed. Furthermore, we consider the problem of testing homogeneity of parameters against the simple order restriction. We give the likelihood ratio (LR) test statistic for the testing problem and derive its asymptotic null distribution.     

Parameter Estimation for the NEAR（p） Model

As to the acronym NEAR(p), it means "New Exponential Autoregressive Process of order p". The NEAR(p) model is denned by where α0,α1,α2… are non-negative and sum to unity, and the residual sequence{εt} is defined as where q1, q2, … , qp+1 are non-negative and sum to unity, and {Et} is an independent and identically distributed (i.i.d.) sequence of standard exponential variants. Chan showed necessary and sufficient conditions for the existence of a stationary and ergodic NEAR(p) model.     

OD-CHARACTERIZATION OF ALMOST SIMPLE GROUPS RELATED TO U6（2）

Let G be a finite group and π(G) = { p 1 , p 2 , ··· , p k } be the set of the primes dividing the order of G. We define its prime graph Γ(G) as follows. The vertex set of this graph is π(G), and two distinct vertices p, q are joined by an edge if and only if pq ∈π e (G). In this case, we write p ～ q. For p ∈π(G), put deg(p) := |{ q ∈π(G) | p ～ q }| , which is called the degree of p. We also define D(G) := (deg(p 1 ), deg(p 2 ), ··· , deg(p k )), where p 1 < p 2 < ··· < p k , which is called the degree pattern of G. We say a group G is k-fold OD-characterizable if there exist exactly k non-isomorphic finite groups with the same order and degree pattern as G. Specially, a 1-fold OD-characterizable group is simply called an OD-characterizable group. Let L := U 6 (2). In this article, we classify all finite groups with the same order and degree pattern as an almost simple groups related to L. In fact, we prove that L and L.2 are OD-characterizable, L.3 is 3-fold OD-characterizable, and L.S 3 is 5-fold OD-characterizable.     

Quasi-maximum likelihood estimators in generalized linear models with autoregressive processes

The paper studies a generalized linear model(GLM)y_t = h(x_t~T β) + ε_t,t = l,2,...,n,where ε_1 = η_1,ε_1 =ρε_t +η_t,t = 2,3,...;n,h is a continuous differentiable function,η_t's are independent and identically distributed random errors with zero mean and finite variance σ~2.Firstly,the quasi-maximum likelihood(QML) estimators of β,p and σ~2 are given.Secondly,under mild conditions,the asymptotic properties(including the existence,weak consistency and asymptotic distribution) of the QML estimators are investigated.Lastly,the validity of method is illuminated by a simulation example.     

THE CONVERGENCE RATES OF EMPIRICAL BAYES ESTIMATION FOR PARAMETERS OF TWO-SIDED TRUNCATION DISTRIBUTION FAMILIES

Consider the two-sided truncation distribution families written in the form f(x,θ)=w(θ_1, θ_2)·h(x)I_([θ_1,θ_2])(x)dx, where θ=(θ_1,θ_2). T(X)=(t_1(X), t_2(X))=(min(X_1, …, X_m), max(X_1, …, X_m)) is a sufficient statistic and we denote its marginal density by f(t)dμ~T. The prior distribution of θ belong to the famlly. In this paper, we have constructed the empirical Bayes (EB) estimator of θ, φ_n(t), by using the kernel estimation of f(t) and established its convergence rates. Under suitable conditions it is shown that the rates of convergenc of EB estimator are O(N~-((λ中-1)(k 1))/(2(k 2)k)), where the neural number k>1 and 1/2<λ<1-1/2k. Finally an example about this result is given.     

光滑函数类中一族无高阶导数的大范围收敛迭代法

The problem whether the iteration formula with the global convergence which does notneed to compute the second order derivative of the function can be found, raised in [7], issolved for f(x)∈C~1(R~1) in the present paper by using the methods of prior estimates andintroducing a parametric function. The main results are as follows: 1. For f(x)∈C~1(R~1), the families of iteration formulas of the global convergence,without derivatives of higher order, are suggested in the following formx_(n 1)=x_n±|f(x_n)|/|f'(x_n)| α(x_n)|f(x_n)|,(1)x_(n 1)=x_n-α|f(x_n)|/(α-1)f'(x_n)sgnf(x_0)±(f'2(x_n)αp(x_n)|f(x_n)|),(2)x_(n 1)=x_n±|f(x_n)f'(x_n)|/f'2(x_n) 1/2p(x_n)|f(x_n)|,(3)Where the real parameter a∈(0, 2] and the real parametric functions α(x)=α(f(x),f'(x)) (>0) and p(x)= p(f(x), f,(x)) (>0) with certain arbitrariness are continuous orpiecewise continuous. 2. The convergence order of the iteration sequence {x_n} generated by (1), (2) or (3)is 2 for a simple real zero of f(x), and is 1 for a multiple zero.     

The Gleason''''s problem for some polyharmonic and hyperbolic harmonic function spaces

LetΩ Rn be a bounded convex domain with C2 boundary. For 0相似文献   

ON THE ORDER OF SUMMABILITY OF THE FOURIER INVERSION FORMULA

In this article we show that the order of the point value, in the sense of Lojasiewicz, of a tempered distribution and the order of summability of the pointwise Fourier inversion formula are closely related. Assuming that the order of the point values and certain order of growth at infinity are given for a tempered distribution, we estimate the order of summability of the Fourier inversion formula. For Fourier series, and in other cases, it is shown that if the distribution has a distributional point value of order k, then its Fourier series is e.v. Cesaro summable to the distributional point value of order k＋1. Conversely, we also show that if the pointwise Fourier inversion formula is e.v. Cesaro summable of order k, then the distribution is the （k ＋ 1）-th derivative of a locally integrable function, and the distribution has a distributional point value of order k ＋ 2. We also establish connections between orders of summability and local behavior for other Fourier inversion problems.     

A Class of Multiderivative Hybrid One-step Methods

This paper presents a class of hybrid one-step methods that are obtained by using Cramer's rule and rational approximations to function exp(q). The algorithms fall into the catalogue of implicit formula, which involves sth order derivative and s 1 free parameters. The order of the algorithms satisfies s 1≤p≤2s 2. The stability of the methods is also studied, necessary and sufficient conditions for A-stability and L-stability are given. In addition, some examples are also given to demonstrate the method presented.     

中心对称本原矩阵的k点指数集

Let G = (V, E) be a primitive digraph. The vertex exponent of G at a vertex v ∈ V, denoted by expG(v), is the least integer p such that there is a v → u walk of length p for each u ∈ V. We choose to order the vertices of G in the k-point exponent of G and is denoted by expG(k), 1 ≤ k ≤ n. We define the k-point exponent set E(n, k) := {expG(k)| G = G(A) with A ∈ CSP(n)}, where CSP(n) is the set of all n × n central symmetric primitive matrices and G(A) is the associated graph of the matrix A. In this paper, we describe E(n,k) for all n, k with 1 ≤ k ≤ n except n ≡ 1(mod 2) and 1 ≤ k ≤ n - 4. We also characterize the extremal graphs when k = 1.     

Dynamics of a Function Related to the Primes

Let n = p1p2 ··· pk, where pi(1 ≤ i ≤ k) are primes in the descending order and are not all equal. Let Ωk(n) = P(p1 + p2)P(p2 + p3) ··· P(pk-1+ pk)P(pk+ p1), where P(n) is the largest prime factor of n. Define w0(n) = n and wi(n) = w(wi-1(n)) for all integers i ≥ 1. The smallest integer s for which there exists a positive integer t such thatΩs k(n) = Ωs+t k(n) is called the index of periodicity of n. The authors investigate the index of periodicity of n.     

The k-point Exponent Set of Primitive Digraphs with Girth 2

Let D =(V,E)be a primitive digraph.The vertex exponent of D at a vertex v∈V,denoted by exPD(V),is the least integer p such that there is a v→u walk of length p for each u∈V.Following Brualdi and Liu,we order the vertices of D so that exPD(v_1)≤exPD(v_2)≤…≤exPD(v_n).Then exPD(v_k)is called the k- point exponent of D and is denoted by exP_D(k),1≤k≤n.In this paper we define e(n,k):=max{exp_D(k)|D∈PD(n,2)} and E(n,k):= {expD(k)|D∈PD(n,2)},where PD(n,2)is the set of all primitive digraphs of order n with girth 2.We completely determine e(n,k)and E(n,k)for all n,k with n≥3 and 1≤k≤n.     

On Some Cycles in Wenger Graphs

Let p be a prime,q be a power of p,and let Fq be the field of q elements.For any positive integer n,the Wenger graph Wn(q)is defined as follows:it is a bipartite graph with the vertex partitions being two copies of the(n+1)-dimensional vector space Fq^n+1,and two vertices p=(p(1),…,p(n+1))and l=[l(1),…,l(n+1)]being adjacent if p(i)+l(i)=p(1)l(1)i-1,for all i=2,3,…,n+1.In 2008,Shao,He and Shan showed that for n≥2,Wn(q)contains a cycle of length 2 k where 4≤k≤2 p and k≠5.In this paper we extend their results by showing that(i)for n≥2 and p≥3,Wn(q)contains cycles of length 2k,where 4≤k≤4 p+1 and k≠5;(ii)for q≥5,0相似文献   

A COMPARISON OF FORECASTING MODELS OF THE VOLATILITY IN SHENZHEN STOCK MARKET

Based on the weekly closing price of Shenzhen Integrated Index, this article studies the volatility of Shenzhen Stock Market using three different models: Logistic, AR(1) and AR(2). The time-variable parameters of Logistic regression model is estimated by using both the index smoothing method and the time-variable parameter estimation method. And both the AR(1) model and the AR(2) model of zero-mean series of the weekly closing price and its zero-mean series of volatility rate are established based on the analysis results of zero-mean series of the weekly closing price. Six common statistical methods for error prediction are used to test the predicting results. These methods are: mean error (ME), mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE), Akaike's information criterion (AIC), and Bayesian information criterion (BIC). The investigation shows that AR(1) model exhibits the best predicting result, whereas AR(2) model exhibits predicting results that is intermediate between AR(1) model and the Logistic regression model.     

有约束多元回归分析中的C_p统计量

In this paper, Mallow's C_p statistic in multiple linear regression analysis is genera-lized to the case with linear equality constrained conditions.The C_(p,m_1) statistic is introduced asC_(p,m_1)=RS_p~2/σ~2-m 2(p-m_1),where m and m_1 are respectively the numbers of the observed data of the variables andof the constrained conditions, p>m_1 is the number of the remaining regression variablesafter q variables are rejected from the n regression variables (p q=n) RS_p~2 is the sumof squares of residuals of the regression for the p remaining variables, σ~2 is an unbiasedestimate of variance σ~2. The properties of the C_(p,m_1) statistic and a method for selectingand analyzing variables in constrained multiple linear regression analysis by using theC_(p,m_1) statistic are discussed in detail.     

无$K_{1,4}$子图的图的路覆盖

For a graph G, a path cover is a set of vertex disjoint paths covering all the vertices of G, and a path cover number of G, denoted by p(G), is the minimum number of paths in a path cover among all the path covers of G. In this paper, we prove that if G is a K_(1,4)-free graph of order n and σ_(k+1)(G) ≥ n-k, then p(G) ≤ k, where σ_(k+1)(G) = min{∑v∈S d(v) : S is an independent set of G with |S| = k + 1}.     

改进的自回归过程结构变点检验

In this paper, we consider the problem of detecting for structural changes in the autoregressive processes including AR（p） process. In performing a test, we employ the conventional residual CUSUM of squares test （RCUSQ） statistic. The RCUSQ test is based on the subsampling method introduced by Jach and Kokoszka [J. Methodology and Computing in Applied Probability 25（2004）]. It is shown that under regularity conditions, the asymptotic distribution of the test statistic is the function of a standard Brownian bridge. Simulation results as to AR（1） process and an example of real data analysis are provided for illustration.     

Maximal Dimension of Invariant Subspaces to Systems of Nonlinear Evolution Equations

In this paper,the dimension of invariant subspaces admitted by nonlinear systems is estimated under certain conditions.It is shown that if the two-component nonlinear vector differential operator F=(F 1,F 2) with orders {k 1,k 2 } (k 1 ≥ k 2) preserves the invariant subspace W 1 n 1 × W 2 n 2 (n 1 ≥ n 2),then n 1 n 2 ≤ k 2,n 1 ≤ 2(k 1 + k 2) + 1,where W q n q is the space generated by solutions of a linear ordinary differential equation of order n q (q=1,2).Several examples including the (1+1)-dimensional diffusion system and Ito 's type,Drinfel'd-Sokolov-Wilson's type and Whitham-Broer-Kaup's type equations are presented to illustrate the result.Furthermore,the estimate of dimension for m-component nonlinear systems is also given.     

The Rainbow Vertex-disconnection in Graphs

Let G be a nontrivial connected and vertex-colored graph. A subset X of the vertex set of G is called rainbow if any two vertices in X have distinct colors. The graph G is called rainbow vertex-disconnected if for any two vertices x and y of G, there exists a vertex subset S of G such that when x and y are nonadjacent, S is rainbow and x and y belong to different components of G-S; whereas when x and y are adjacent, S + x or S + y is rainbow and x and y belong to different components of(G-xy)-S. For a connected graph G, the rainbow vertex-disconnection number of G, denoted by rvd(G), is the minimum number of colors that are needed to make G rainbow vertexdisconnected. In this paper, we characterize all graphs of order n with rainbow vertex-disconnection number k for k ∈ {1, 2, n}, and determine the rainbow vertex-disconnection numbers of some special graphs. Moreover, we study the extremal problems on the number of edges of a connected graph G with order n and rvd(G) = k for given integers k and n with 1 ≤ k ≤ n.     

Conjecture on Self Hamiltonian Path Graph

The Hamiltonian path graph H(G) of a graph G isa that graph having the samevertex set as G and in which two vertices u and v are adjacent if and only if Gcontains a Hamiltonian u - v path. A graph G is a self-Hamiltonian path graph ifG≌H(G).G. Chartrand conjecture: A graph G of order p is a self-Hamiltonian path:graph if and only if G is chord additive or G is isomorphic to one of the graphsK_p, (?)_p, C_p(p≥3),K((1/2)p, (1/2)p), and K_(p/2) (?)_(p/2),the last two for even P.