Modelling Specific Interest Rate Risk with Estimation of Missing Data

For the treatment of specific interest rate risk, a risk model is suggested, quantifying and combining both market and credit risk components consistently. The market risk model is based on credit spreads derived from traded bond prices. Though traded bond prices reveal a maximum amount of issuer specific information, illiquidity problems do not allow for classical parameter estimation in this context. To overcome this difficulty an efficient multiple imputation method is proposed that also quantifies the amount of risk associated with missing data. The credit risk component is based on event risk caused by correlated rating migrations of individual bonds using a Copula function approach.     

基于区间数据最大似然估计的新方法

In this paper, we study the two-parameter maximum likelihood estimation (MLE)problem for the GE distribution with consideration of interval data. In the presence of interval data, the analytical forms for the restricted MLE of the parameters of GE distribution do not exist. Since interval data is kind of incomplete data, the EM algorithm can be applied to compute the MLEs of the parameters. However the EM algorithm could be less effective.To improve effectiveness, an equivalent lifetime method is employed. The two methods are discussed via simulation studies.     

数据分组和右截尾情形下混合指数分布的参数估计

混合模型是可靠性工程,金融保险和计量经济学等领域中的一类重要模型。本文利用EM算法考虑了混合指数分布在分组数据和右截尾情形下的参数估计问题,并给出了相应的参数估计公式,最后的数值模拟表明EM算法对我们的模型是有效的。     

基于实测高光谱和电磁感应数据的区域土壤盐渍化遥感监测研究

以新疆渭干河—库车河三角洲绿洲为例,利用实测得到的不同盐渍化程度的盐渍土高光谱数据和电磁感应数据(EM38)协同构建土壤高光谱盐分指数遥感监测模型,将该模型通过尺度效应转换用于校正传统的Landsat-TM多光谱遥感影像的土壤盐分光谱指数,用校正过的TM影像进行区域土壤盐分的反演,并利用实测土壤盐分数据对反演结果进行分析与验证。结果表明：将高光谱和电磁感应数据与多光谱遥感技术相结合进行区域土壤盐渍化信息的提取,其精度和反演效果(R2=0.799 3,p<0.01)明显优于传统多光谱遥感方法中单纯利用土壤盐分指数所建立的监测模型(R2=0.587 4,p<0.01),为今后更好地实现土壤盐渍化的高精度遥感动态监测研究提供了科学依据。     

利用空间点过程提取丛集点算法的适用性研究

以二维泊松过程理论为基础,结合空间点过程理论,引入k阶最近邻距离的概念,介绍了基于k阶最近距离的丛集点的提取算法,对该算法的适用范围进行了讨论和分析,发现丛集区域和背景区域疏密程度差异以及所研究的数据点数目对该方法有影响,疏密程度差异较小时,该算法的有效性不强,疏密程度差异较大时,该算法较为适用,同时,数据点的总数不同时,算法的适用范围有所差异,但差异不大.此外,引入权重的思想,对算法中理想数据点的设置进行了一定程度的拓展,将所研究区域内的数据点赋予不同的权重,进行丛集数据点的提取,从而扩展了该算法的使用范围. 关键词： 丛集点 最近邻距离 EM算法 分布参数比值     

FDTD simulation study of size/gap and substrate-dependent SERS activity study of Au@SiO_2 nanoparticles

We use Au@SiO_2 nanoparticles(NPs) to systematically and comprehensively study the relationship between nanostructure and activity for surface-enhanced Raman scattering. Calculation simulation using the finite different time domain method verifies the experiment results and further reveals that the particle size and the distance between the NPs play vital roles in the surface-enhanced Raman scattering(SERS). Furthermore, in order to better simulate the real experiment, a Au@SiO_2 nanosphere dimer is placed on the silicon substrate and Au substrate, separately. The simulation results show that the large EM field coupling is due to the "hot spots" transferred from the NP–NP gaps to NP–surface of metal gaps,meanwhile, more "hot spots" occur. We also find that the signal intensity strongly depends on the position of the probe molecule. This work provides a better understanding of EM field enhancement.     

磷石膏中微量含氟物相的光谱分析

磷石膏中二水硫酸钙(CaSO₄·2H₂O)的含量高达90%以上,是一种重要的再生石膏资源。然而与天然石膏不同,磷石膏中磷、氟、有机物等有害杂质限制了它的实际利用。探明微量杂质氟物相的存在形态、含量及分布规律,对高效脱除磷石膏中杂质氟具有重要的理论价值。采用X射线光电子能谱(X-ray photoelectron spectroscopy, XPS)与电子显微探针(electron microprobe analysis, EMPA)相结合的分析方法,研究了磷石膏中微量含氟物相的主要存在形式和分布规律。结果表明,磷石膏中微量含氟物相主要包括NaF,KF,CaF₂,K₂SiF₆,Na₂SiF₆,Na₃AlF₆,K₃AlF₆,AlF₃·3H₂O,AlF_2.3(OH)_0.7·H₂O,Ca₅(PO₄)₃F,Ca₁₀(PO₄)₆F₂。其中,4.83%的氟以NaF,KF,CaF₂等氟化物形式存在,8.42%的氟以氟磷酸盐Ca₅(PO₄)₃F和Ca₁₀(PO₄)₆F₂形式存在,12.21%的氟以氟铝酸盐Na₃AlF₆和K₃AlF₆形式存在,41.52%的氟以氟硅酸盐K₂SiF₆和Na₂SiF₆形式存在,33.02%的氟以带结晶水的氟化铝AlF₃·3H₂O和AlF_2.3(OH)_0.7·H₂O形式存在。研究表明分析固体样品中微量元素物相时,采用XPS与EMPA相结合的分析方法更具有优势。本研究为磷石膏中微量杂质氟的脱除以及有效回收氟资源提供理论依据。     

Chirofibers with helical windings - An analytical investigation

In this communication, the propagation characteristic of a chiral fiber having helical windings at the core-cladding boundary is analyzed in respect of the relative distribution of power over the sustained modes. The core and the cladding sections of the chirofiber are assumed to have different chirality admittance values while the helical winding pitch angle is considered to attain two particular values -0^° and 90°. It is observed that the introduction of helical structure leaves a dominant effect on the relative power distribution of the chiral fiber as the variations of the confinement factor with the allowed values of the propagation constants corresponding to different azimuthal modes exhibit much difference in nature for different values of the angle of pitch. It is noticed that the power confinement in the core is much higher when the pitch angle of the helix is effectively introduced by keeping the windings perpendicular to the propagation direction. Further, the property of mode degeneracy in chirofibers is also observed, which is reported to be of much significance when the helical structure remains parallel to the direction of propagation. A more profound mode degeneration characteristic is found for the chiral fiber with larger core dimension.     

Positron Emission Tomography and Random Coefficients Regression

We further explore the relation between random coefficients regression (RCR) and computerized tomography. Recently, Beran et al. (1996, Ann. Statist., 24, 2569–2592) explored this connection to derive an estimation method for the non-parametric RCR problem which is closely related to image reconstruction methods in X-ray computerized tomography. In this paper we emphasize the close connection of the RCR problem with positron emission tomography (PET). Specifically, we show that the RCR problem can be viewed as an idealized (continuous) version of a PET experiment, by demonstrating that the nonparametric likelihood of the RCR problem is equivalent to that of a specific PET experiment. Consequently, methods independently developed for either of the two problems can be adapted from one problem to the other. To demonstrate the close relation between the two problems we use the estimation method of Beran, Feuerverger and Hall for image reconstruction in PET.     

Nonlinear Smoothing and the EM Algorithm for Positive Integral Equations of the First Kind

We study a modification of the EMS algorithm in which each step of the EMS algorithm is preceded by a nonlinear smoothing step of the form , where S is the smoothing operator of the EMS algorithm. In the context of positive integral equations (à la positron emission tomography) the resulting algorithm is related to a convex minimization problem which always admits a unique smooth solution, in contrast to the unmodified maximum likelihood setup. The new algorithm has slightly stronger monotonicity properties than the original EM algorithm. This suggests that the modified EMS algorithm is actually an EM algorithm for the modified problem. The existence of a smooth solution to the modified maximum likelihood problem and the monotonicity together imply the strong convergence of the new algorithm. We also present some simulation results for the integral equation of stereology, which suggests that the new algorithm behaves roughly like the EMS algorithm. Accepted 1 April 1997