Asymptotics of estimates in constrained nonlinear regression with long-range dependent innovations

The purpose of this paper is to investigate the asymptotic properties of the least squares estimates (L ₂-estimates) and the least absolute deviation estimates (L ₁-estimates) of the parameters of a nonlinear regression model subject to a set of equality and inequality restrictions, which has a long-range dependent stationary process as its stochastic errors. Then we will compare the asymptotic relative efficiencies of the above estimators.     

Fractional Brownian Heavy Traffic Approximations of Multiclass Feedforward Queueing Networks

We consider multiclass feedforward queueing networks under first in first out and priority service disciplines driven by long-range dependent arrival and service time processes. We show that in critical loading the normalized workload, queue length and sojourn time processes can converge to a multi-dimensional reflected fractional Brownian motion. This weak heavy traffic approximation is deduced from a deterministic pathwise approximation of the network behavior close to constant critical load in terms of the solution of a Skorokhod problem. Since we model the doubly infinite time interval, our results directly cover the stationary case.AMS subject classification: primary 90B15, secondary 60K25, 68M20     

Continuous dependence on modelling for a complex Ginzburg–Landau equation with complex coefficients

Continuous dependence on a modelling parameter is established for solutions of a problem for a complex Ginzburg–Landau equation. A homogenizing boundary condition is also used to discuss the continuous dependence results. We derive a priori estimates that indicate that solutions depend continuously on a parameter in the governing differential equation. Copyright © 2004 John Wiley & Sons, Ltd.     

Continuous dependence on the geometry and on the initial time for a class of parabolic problems I

In this paper, we investigate the continuous dependence on the geometry and the initial time for solutions u( x , t) of a class of nonlinear parabolic initial‐boundary value problems. Copyright © 2007 John Wiley & Sons, Ltd.     

Effect of core-shell micelle formation on the redox properties of phenothiazine-labeled poly(ethyl glycidy ether)-block-poly(ethylene oxide)

Redox properties of phenothiazine-labeled poly(ethyl glycidy ether)-block-poly(ethylene oxide) (PT-EGE_n-b-EO_m) are reversibly changed by core-shell micelle formation. In the temperature range higher than the critical micellization temperature (cmt), the anodic potential of PT group positively shifts and concomitantly its anodic current decrease, or levels off compared to those of the reference polymer PT-EO_m without the thermo-responsive EGE_n segment. The former alteration is caused by incorporation of hydrophobic PT groups into a core of the micelle and the latter by the decrease in the diffusion coefficient of PT groups due to formation of the core-shell micelles. The cmt value and the temperature-dependent alteration in the redox properties strongly depend on the polymer structure, especially the length of thermo-responsive EGE_n segment. The electrochemically determined hydrodynamic radii of the polymer aggregates seem to be overestimated, compared to the values reported for the aggregates of other thermo-responsive polymers with similar molecular weights, implying the presence of electrochemically inactive PT groups in the copolymers having longer thermo-responsive segments.     

原子核电荷半径的新公式

结合原子核的电荷半径的实验数据,详细分析了描述原子核电荷半径的经验公式,表明电荷半径的Z^1/3律优于A^1/3律.更细致的考察发现,对于远离β稳定线的核素,电荷半径具有近似线性的同位旋相关性.由此得到的同位旋相关的Z^1/3公式更适合描述原子核的电荷半径.     

沪深股市相关结构分析研究

在金融市场风险分析中,对金融资产相关结构的讨论有着重要意义,从而引出对如何选取好的相关结构模型来捕捉金融资产间的相关变化规律的讨论。针对这一问题,我们用混合相关结构函数Copula对上海、深圳股票市场进行了相关分析研究,用极值分布刻画了每支股票的边缘分布,用两步估计法对Copula中的参数进行了估计。分析结果表明:混合Copula相关结构能够捕捉金融市场间相关性变化规律,比单个Copula相关结构更灵活,更能全面地反映市场间非对称变化的相关程度和模式,此方法还可以推广到对多种金融资产收益率进行相关性分析。     

On existence and stability in the theory of swelling porous elastic soils

The aim of this paper is to introduce a new functional in thestudy of swelling porous elastic soils saturated by a fluid.This new functional is a useful tool; it allows us to provethe existence of solutions in the case of a compressible fluid.We also prove the stability of solutions and the exponentialdecay in the case of an incompressible fluid. We study as wellthe continuous dependence with respect to the initial time.     

Weak-mixing implies sensitive dependence

Let X be a metric space, B the σ-algebra of Borel subsets of X, and μ a probability measure on (X,B). In this note, for a measure-preserving map T (respectively a measure-preserving semi-flow φ) on (X,B,μ), we prove that if suppμ=X, and T (respectively φ) is weak-mixing, then T (respectively φ) has sensitive dependence.     

Long‐range dependence and performance in telecom networks

Telecommunications systems have recently undergone significant innovations. These call for suitable statistical models that can properly describe the behaviour of the input traffic in a network. Here we use fractional Brownian motion (FBM) to model cumulative traffic network, thus taking into account the possible presence of long‐range dependence in the data. A Bayesian approach is devised in such a way that we are able to: (a) estimate the Hurst parameter H of the FBM; (b) estimate the overflow probability which is a parameter measuring the quality of service of a network: (c) develop a test for comparing the null hypothesis of long‐range dependence in the data versus the alternative of short‐range dependence. In order to achieve these inferential results, we elaborate an MCMC sampling scheme whose output enables us to obtain an approximation of the quantities of interest. An application to three real datasets, corresponding to three different levels of traffic, is finally considered. Copyright © 2004 John Wiley & Sons, Ltd.