带ARMA(1,1)条件异方差相关的随机波动模型的MCMC算法

我们首先提出了一个带ARMA(1,1)条件异方差相关的随机波动模型,它是基本的随机波动模型的一个自然的推广.进一步,对于这一新模型,我们给出了一个马尔可夫链蒙特卡罗(M CM C)算法.最后,利用该模型的模拟数据,展示了M CM C算法在这种模型中的应用.     

Automatic detection and identification of shocks in Gaussian state‐space models: a Bayesian approach

An automatic monitoring and intervention algorithm that permits the supervision of very general aspects in an univariate linear Gaussian state–space model is proposed. The algorithm makes use of a model comparison and selection approach within a Bayesian framework. In addition, this algorithm incorporates the possibility of eliminating earlier interventions when subsequent evidence against them comes to light. Finally, the procedure is illustrated with two empirical examples taken from the literature. Copyright © 2005 John Wiley & Sons, Ltd.     

Robust Bayesian Inference for Seemingly Unrelated Regressions with Elliptical Errors

Bayesian inference is considered for the seemingly unrelated regressions with an elliptically contoured error distribution. We show that the posterior distribution of the regression parameters and the predictive distribution of future observations under elliptical errors assumption are identical to those obtained under independently distributed normal errors when an improper prior is used. This gives inference robustness with respect to departures from the reference case of independent sampling from the normal distribution.     

The structure of monolayer SiO2 on Mo(1 1 2): A 2-D [Si-O-Si] network or isolated [SiO4] units?

In this letter, atomically resolved scanning tunneling microscopic (STM) images obtained from monolayer SiO₂/Mo(1 1 2) are presented. The results are consistent with a previously proposed structural model of isolated [SiO₄] units based on vibrational features observed by high-resolution electron energy loss spectroscopy (HREELS) and infrared reflection-absorption spectroscopy (IRAS), and oxygen species identified by ultra-violet photoemission spectroscopy (UPS). These results are inconsistent with a structural model that assumes a two-dimensional (2-D) [Si-O-Si] network. These data illustrate that a metal substrate, although coated with an oxide thin layer, can be directly imaged at the atomic-scale with STM.     

Nonlinear Time Series Analysis Since 1990:Some Personal Reflections

Abstract I reflect upon the development of nonlinear time series analysis since 1990 by focusing on five majorareas of development. These areas include the interface between nonlinear time series analysis and chaos,thenonparametric/semiparametric approach,nonlinear state space modelling,financial time series and nonlinearmodelling of panels of time series.     

New feature in the Auger peak of adsorbed oxygen

Recent joint theoretical and experimental investigations of Auger core-core-valence spectra of alkali adatoms on simple metals have revealed that such technique is capable to ascertain contributions from different adsorption environments in the signal [M.I. Trioni, S. Caravati, G.P. Brivio, L. Floreano, F. Bruno, A. Morgante, Phys. Rev. Lett. 93 (2004) 206802]. Consequently, to verify if such an effect is present also for other chemical species, we study theoretically the KLV transition of oxygen either as a bulk impurity or as an adsorbate in/on Al and Ag (jellium-like). We make use of the Fermi golden rule in which the matrix elements of the interaction are calculated within DFT. We verify that the relevant physical quantity of this phenomenon is the excited local density of states (LDOS), calculated within a region centered on the core ionized atom. The Auger rate for oxygen in Ag bulk displays a single asymmetric peak, while for adsorbed oxygen a second smaller feature at lower energies, and very close to the first one, appears. This unexpected result follows from the removal of the degeneracy of the m quantum number of the 2p states of oxygen at the surface. It is only displayed on the electronically less dense metal (Ag), but not on Al.     

Preliminary results of a non-spherical aerosol method for the retrieval of the atmospheric aerosol optical properties

There is experimental evidence that the non-sphericity of certain atmospheric particles can cause scattering properties different from those predicted by standard Mie theory. Numerous studies indicate the need to consider the presence of non-spherical particles in modeling the optical properties of atmospheric aerosols. On the other hand, natural aerosols show a great variety of shapes, making difficult a realistic choice of a particle shape (or shape mixture) model. In this paper, we test a parameterization of the particle shape in the retrieval of size distribution, phase function, single scattering albedo and asymmetry parameter from direct and sky-radiance measurements. For this purpose we have substituted the Kernel based on the Mie theory included in the model SKYRAD.PACK by one derived for non-spherical particles. The method is applied under different atmospheric conditions, including Saharan dust outbreak, polluted and local mineral episodes. We compare the results with those obtained by the well known spheroids algorithm used in the AERONET network.     

The six-vertex model eigenvectors as critical limit of the eight-vertex model bethe ansatz

The critical limit of the eight-vertex model eigenvectors obtained by means of the generalized Bethe Ansatz is shown to give the six-vertex eigenvectors as constructed in a previous paper by two of the authors. Furthermore, an explicit mapping is established between these eigenvectors and the usual Bethe Ansatz eigenvectors of the six-vertex model. This allows one to show that the indexv labeling the eight-vertex eigenstates becomes exactly the third component of the total spin in the critical limit.     

Quantitative and high mass ToF-SIMS studies of siloxane segregation in hydrogel polymers using cryogenic sample handling techniques

This paper examines the capabilities of cryogenic sample handling to examine composition and structure of hydrogel materials where siloxane components are central to the analysis. XPS analysis of multicomponent polymers with cryogenic sample handling following exposure to aqueous environments has revealed the composition and kinetics of near surface reorganization for siloxane and fluorocarbon containing polymers. In this study we report results from a ToF-SIMS protocol for cryogenic sample handling applied to the analysis of surface changes upon hydration/dehydration of hydrogel polymers. Comparison of results from angle dependent XPS and ToF-SIMS are discussed for a range of commercial soft contact lens materials. Both methods detected changes in surface chemistry between the hydrated (frozen) and dehydrated surfaces. Analysis of the hydrated surfaces detected polymer components indicative of the commercial formulation as well as ice clusters. Analysis of the dehydrated materials detected changes in surface chemistry relative to the hydrated surface in addition to loss of water due to sample dehydration. A quantitative standard additions method for ToF-SIMS data was used to determine submonolayer amounts of PDMS impurities at the surface of the hydrogels. ToF-SIMS analysis of a series of seven poly (allyl methacrylate-g-dimethylsiloxane), AMA-g-DMS, graft copolymers in the hydrated state revealed high mass oligomeric ion distributions for systems with bulk PDMS content greater than 25 wt.%. This marks the first time that detection of high mass oligomeric ion distributions from hydrated (frozen) surfaces has been reported. Analysis of the dehydrated surface detected formation of high mass oligomeric ion distributions for systems with PDMS bulk content greater than 15 wt.%, but only detected these ion distributions in wet (frozen) samples when the bulk concentration was greater than 25 wt.%.     

全面成绩管理的初探

利用数量化方法,数字特征法,W ilcoxon顺序和检验法以及试卷分析的各种方法(试题难度,区分度,信度,效度等),定量地解决了影响学生成绩的主要因素,并引入全面管理方法,明显地改善了学生成绩,学生综合能力明显加强.