基于三类模型的四大银行股票收益率预测研究

运用时间序列分析的预测方法,对四大银行的股票日对数收益率序列进行拟合与预测分析,分别构建ARMA模型、GARCH模型以及ARMA-GARCH组合模型,通过模型比较,实证分析表明:在拟合效果上,ARMA-GARCH模型的拟合优度优于ARMA模型和GARCH模型;在预测效果上,ARMA模型的预测效果最优,ARMA-GARCH模型次之.     

Testing coefficients of AR and bilinear time series models by a graphical approach

AR and bilinear time series models are expressed as time series chain graphical models, based on which, it is shown that the coefficients of AR and bilinear models are the conditional correlation coefficients conditioned on the other components of the time series. Then a graphically based procedure is proposed to test the significance of the coefficients of AR and bilinear time series. Simulations show that our procedure performs well both in sizes and powers. This work was supported by the Hong Kong Polytechnic University Research Council, the National Natural Science Foundation of China (Grant No. 10671044) and the Science and Technology Bureau of Guangzhou Municipal Government of China (Grant No. LSBH-017)     

基于灰色微分方程的传染病预测

本文归纳总结了传染病的几类预测方法,并通过一个例子,将灰色模型和微分方程模型结合,用于传染病的预测.     

2011年研究生建模竞赛B题的评阅综述

本题从一项科研项目中提炼、并结合目前成为关注热点的隐身技术而设计,侧重于数学建模.结合题中的2个问题,可以抽象出3个平时比较少见的数学模型:几何模型,反射投影模型和积分方程模型.在竞赛中,前2个模型都有部分同学正确地得出,可惜的是,问题2所要求的积分方程模型,在近500份答卷,却无人得出,甚为遗憾.问题2属于一个需要同时确定数个彼此关联影响的函数的问题,处理这样问题的基本方法是建立以这些函数为变量的方程组,在这里由于确定相互影响的定量关系必须用积分,所以最终得出的是一个积分方程组.微分积分是大学数学中最基本最重要的概念和方法,由此不难看出,我们的基础教育中的弊病与问题,这需要引起有识之士们的反思.     

Testing coeffcients of AR and bilinear time series models by a graphical approach

AR and bilinear time series models are expressed as time series chain graphical models, based on which, it is shown that the coefficients of AR and bilinear models are the conditional correlation coefficients conditioned on the other components of the time series. Then a graphically based procedure is proposed to test the significance of the coeffcients of AR and bilinear time series. Simulations show that our procedure performs well both in sizes and powers.     

PM2.5相关因素及分布演变的研究

以武汉市和西安市的PM2.5检测点数据及气象数据作为基础,建立了相关性分析模型,灰色关联度模型,混合回归模型,高斯烟羽模型,分期治理最优化模型等模型,通过定量与定性分析的方法,从PM2.5的相关因素、分布与演变、控制管理三个方面,对两个市的PM2.5进行了深入的研究与探讨.     

非线性非均衡蛛网模型的动态分析

描述单商品市场价格波动的蛛网模型是动态经济分析中的经典模型 ,证明了由模型 ( )所生成的价格序列在一定的条件下不会出现 3以上周期运动和混沌现象 ,并对其进行稳定性分析 ,得到模型关于均衡价格稳定的六个判别定理 .     

基于参数模型的EVaR风险度量计算方法及实证研究

针对EVaR(Expectile-based Value at Risk)风险度量提出了基于GARCH类和SV波动率模型的EVaR风险度量计算方法,即EVaR计算的参数模型方法.并基于模拟学生t分布时间序列数据,给出EVaR样本外预测的失败率检验方法:Kupiec失败率检验和动态分位数(DQ)检验法.与采用CARE(Conditional Autoregressive Expectile)模型的EVaR计算方法进行了对比研究,结果表明基于GARCH类模型和SV模型相对于基于CARE模型有更优的EVaR预测效果.选取2004年1月5日到2009年12月30日的国内外五个股票市场指数数据,针对日对数收益率进行了EVaR风险度量的实证研究,得出在金融危机期间,基于参数模型的EVaR预测要比基于CARE模型的EVaR预测更接近市场实际风险.     

基于HP-ENN-MC模型降雨量预测

综合HP滤波、Elman神经网络、马尔科夫链的优点建立HP-ENN-MC模型对某地区10年内降雨量进行预测.以某地区1990-2015年植物生育期(6-10月)的降雨量数据作为实验训练样本,以2010-2015年(6-10月)的降雨量数据为实验的测试样本,证明HP-ENN-MC模型的实用性.由最后实验结果得到,预测平均相对误差为3.83%.所建模型能够对降雨量准确预测,与Elman、ENN-MC模型相比,HP-ENN-MC模型对降雨量预测更有效.     

我国房地产行业问题研究

结合数学、计量经济学和国民经济核算等方面的知识,分别从四个方面系统地研究了房地产行业的相关问题,首先,考虑到我国房地产市场存在地区差异性,利用地理加权回归方法(GWR)分别建立房地产行业需求和供给模型来反映该行业市场供需状况;其次,基于VAR模型分区域建立有效的房地产行业定价模型对未来房价走向进行预测,以西部地区的货币供应量对房价的影响为例,其滞后一期的货币供应量发生1个单位的正向变动,房价发生0.85个单位的正向变动;再次,对房地产行业关联度和发展态势建立了投入产出模型和固定效应的变系数面板数据模型,研究发现房地产行业与金融业、租赁和商务服务业、建筑业存在显著关联度,且根据固定效应的变系数面板数据模型结果,可具体分析房地产行业增加值的提高对其他行业的影响程度;最后,基于熵值法建立综合评价模型对天津市房地产行业的可持续发展性进行了研究和深入探讨.     

基于改进Bass模型的多元技术创新扩散研究

鉴于目前并没有一个统一的模型来包含多元技术创新之间的互补性、替代性和竞争性关系,从放宽Bass模型的创新扩散独立性假设条件入手,在原有的创新需求、模仿需求基础上,引入渗透需求,构建包含多元技术创新之间的互补性、替代性和竞争性关系的统一模型--MTID模型(Multi-Technolo-gy Innovation Dif...     

论AMSAA—BISE模型—兼答梅文华

用另一种方法了AMSAA－BISE模型,这无疑表明AMSAA－BISE模型是正确的,并指出梅文华的近似模型的错误,还用工程实例说明这些结论,最后对AMSAA与AMSAA－BISE模型的优缺点进行了讨论。     

ARCH族模型对沪市行业指数收益率的实证研究

本文利用ARCH族模型研究沪市行业指数收益率的波动性.通过对各行业指数收益率的分析发现,行业指数收益率是平稳的,但其条件方差是尖峰厚尾的非正态分布且具有明显的ARCH效应.行业指数收益率均具有不同程度"杠杆"效应.外部信息对公用指数和综合指数收益率影响最大.融入相同的风险,它们收益最高.地产指数对外部信息反应迟钝,收益率也不显著.     

Full backward non-homogeneous semi-Markov processes for disability insurance models: A Catalunya real data application

In this paper a stochastic model for disability insurance contracts is presented. The model is based on a discrete time non-homogeneous semi-Markov process to which the backward recurrence time process is joined. This permits us to study in a more complete way the disability evolution and to face the duration problem in a more effective way. The model is applied to a sample of contracts drawn at random from a mutual insurance company.     

Semi- and Nonparametric Modeling of Ordinal Data

Parametric models for categorical ordinal response variables, like the proportional odds model or the continuation ratio model, assume that the predictor is given by a linear form of covariates. In this article the parametric models are extended to include smooth components in a semiparametric or partially parametric fashion. Parts of the covariates are thereby modeled linearly while other covariates are modeled as unspecified but smooth functions. Estimation is based on a combination of local likelihood and profile likelihood and asymptotic properties of the estimates are derived. In a simulation study it is demonstrated that the profile likelihood approach is to be preferred over a backfitting procedure. Two data examples demonstrate the applicability of the models.     

最优组合预测模型的构建及其应用研究

由于证券价格是随机游走的,在证券定价研究中RBF神经网络模型、灰色GM（1,1）模型、ARIMA模型不具备时效性,通过对上述三个模型进行综合分析,结合三者中有用的信息集合,构建一个最优组合预测模型．在此基础上选取了深发展A在2007年全年的收盘价作为研究样本对这四个模型进行实证研究,研究结果发现,最优组合预测方法对证券价格进行预测具有很好的预测精度和很高的可靠性．     

大数据背景下水厂自动投矾模型研究

根据某市自来水有限责任公司第二水厂的历史矾耗数据，建立矾耗流量关于原水浊度、温度等的动态矾耗模型. 通过对数据进行处理得到10900个合格且净水效果高效的数据，将筛选出的数据分为训练样本集和测试样本集. 在回归拟合中，通过拟合R2的大小将原水浊度划分为“低浊”“中浊”“高浊”3个区间，利用泰勒展开公式的非线性变量代换分别对3个区间建立不同的多项式回归模型，得到预测正确率约为72%，总的矾耗流量值约减少了9.6%的结果；在随机森林模型中，使用10900个合格数据，利用训练样本集，以“原水浊度”“pH值”“原水流量”和“水温”为输入变量，建立包含2000棵决策树的随机森林模型，得到预测正确率约为44. 21%，总的矾耗流量值增加了0.04%的结果. 从模型对合格数据的拟合优度看，随机森林模型比非线性回归模型效果更好；在平均绝对误差、平均绝对偏差百分比等评价指标上，前者均优于后者；但从历史数据检验的结果，模型的可解读性，模型的操作难度和推广角度看，分段二元非线性回归模型的优势更为突出.     

Verhulst模型、微分模型及时滞模型的建模与经济预测应用

经济预测中常常会遇到外生变量的确定问题，由于累积误差和传递误差的存在而很困难，因而需要其它方法，为此我们引入Ｖｅｒｈｕｌｓｔ模型来描述经济过程的动态特征，并用阶数不超过３的微分模型发展了这一思想以便描述，同时具有趋势变动和周期性扰动的数据结构，这是一种非常普遍的情形．然后我们证明了微分模型与时滞模型是等价的，而后者的参数估计极为简单．     

A hybrid macroscopic-based model for traffic flow in road networks

Recently, the unquestionable growth of interest to increase the operational efficiency and capability of transportation systems led to the development of a large number of traffic modeling theories. One of the major operational issues when developing a transportation system management model lies in the selection of the appropriate methodological approach with respect to several decisions, such as the selection of the type of input and output data as well as the qualitative representation and the computational power of the model. Despite the considerable effort in the area, there is still not an approach which per se models effectively the various dynamically evolving features of traffic in road networks. The present paper addresses this issue by introducing a new hybrid approach which combines the complementary features and capabilities of both continuum mathematical models e.g. 1, 6, 23 and 26 and knowledge-based models e.g. 7, 22 and 28 in order to describe effectively traffic flow in road networks.     

Pre-elimination approach to the modelling of segmented representations of cable shape with application to the positioning of a towed sensor

Discrete models for the determination of cable shapes and tensions require the solution of large systems of nonlinear algebraic equations. In these the unknowns are the orientations and coordinates of the segments as well as their tensions. Smaller systems of algebraic equations are obtained by the pre-elimination of the tensions and the coordinates for the lumped mass and rod models which leave the orientation variables as the only unknowns. Furthermore, this pre-elimination analysis yields conditions for the equivalence of the lumped mass and the rod models. This method is applied to the determination of the position of a towed underwater sensor used for seabed mapping or for oceanographic recordings.