Numerical optimization and surface estimation with imprecise function evaluations

This paper presents an investigation of a method for minimizing functions of several parameters where the function need not be computed precisely. Motivated by problems requiring the optimization of negative log-likelihoods, we also want to estimate the (inverse) Hessian at the point of minimum. The imprecision of the function values impedes the application of conventional optimization methods, and the goal of Hessian estimation adds a lot to the difficulty of developing an algorithm. The present class of methods is based on statistical approximation of the functional surface by a quadratic model, so is similar in motivation to many conventional techniques. The present work attempts to classify both problems and algorithmic tools in an effort to prescribe suitable techniques in a variety of situations. The codes are available from the authors' web site http://macnash.admin.uottawa.ca/~rsmin/.     

On regression-based tests for persistence in logarithmic volatility models

Building on the work of Pantula (1986), this paper discusses how the hypothesis of conditional variance nonstationarity in the logarithmic family of generalized autoregressive conditional heteroskedasticity (GARCH) and stochastic volatility processes may be tested using regression-based tests. The latter are easy to implement, have well-defined large-sample distributions, and are less sensitive to structural changes than tests based on the quasimaximum likelihood estimator.     

Price controls, trade protectionism and political business cycles in the U.S. steel industry

The U.S. steel industry is subject to a microeconomic political business cycle resulting from U.S. Presidents designing protectionist policies on behalf of the steel industry; experiencing complaints from consumers and foreign producers as a result of the policy; modifying the policy which results in complaints from the steel industry; and finally, maneuvering policy back in favor of the industry to achieve re-election. Using a cointegrating vector error correction framework, this paper tests the hypothesized political business cycle for its effect on steel prices. We find that trade protectionism does not seem to have succeeded in its primary objective of supporting prices. By expending so much political capital on ineffective trade protection, the steel industry may have lost the opportunity to focus on more substantive issues that might have restrained factor cost and enhanced its competitive ability. The devolution of the steel industry, ironically, may have resulted from it's persistent pleas for protection. Political business cycles in the steel industry, with all its attendant negative consequences, would not occur if the steel industry did not continually lobby for protection.     

Nonparametric Instrumental Variables Estimation of a Quantile Regression Model

We consider nonparametric estimation of a regression function that is identified by requiring a specified quantile of the regression “error” conditional on an instrumental variable to be zero. The resulting estimating equation is a nonlinear integral equation of the first kind, which generates an ill‐posed inverse problem. The integral operator and distribution of the instrumental variable are unknown and must be estimated nonparametrically. We show that the estimator is mean‐square consistent, derive its rate of convergence in probability, and give conditions under which this rate is optimal in a minimax sense. The results of Monte Carlo experiments show that the estimator behaves well in finite samples.     

马云现象的科学价值和文化思考

提出了一种新型钢结构梁柱连接节点——方钢管榫卯节点。对由该节点连接的钢框架结构进行了静力载荷试验,得到梁跨中和端部节点荷载 位移曲线,以及框架不同部位荷载和应变图,分析了试验的结果;并根据试验模型进行了计算机非线性有限元分析,分析了节点处构件不同截面尺寸对节点承载力的影响。提出了方钢管榫卯节点承载力的计算公式,并将它与试验结果进行了比较,比较接近。试验表明 :这种新型榫卯节点承载力高,从设计原则看是可行的。     

经济开放和城乡收入差距的非线性关系：基于省际面板数据的实证研究

经济开放可以通过两个途径影响收入分配：Stolper-Samuelson定理能缩小城乡收入差距而经济开放引致的技术进步效应能扩大城乡收入差距。本文将经济开放分为贸易开放和外资开放,利用我国1995～2005年间省际面板数据对此进行实证研究,发现两者均和城乡收入差距之间存在U型非线性关系。所幸的是我国大多数地区目前仍处在U型关系的左边,因此在我国经济开放能缩小城乡收入差距。     

基于Normal Form理论的电力系统3阶解析解

在对电力系统动态方程进行泰勒级数展开的基础上,运用normal form理论推导出其3阶解析解。分别对单机无穷大系统和2区域4机系统进行了仿真,通过在时域和频域定义的两个近似度指标对比分析线性解析解,2阶解析解及3阶解析解在分析电力系统受扰后的动态特性精确性。并且应用prony算法对仿真结果进行定量分析,检测到了数值积分解中高阶复合模态的存在。从而,验证了推导的3阶解析解对受扰后系统进行分析的有效性。     

基于独立分量分析的降噪技术

介绍了新兴的独立分量分析技术的基本概念和原理,以及具有代表性的算法,即FastICA算法、EASI算法、非线性PCA算法和基于自然梯度的最大似然估计算法。通过降噪仿真实验,并采用均方误差作为降噪的性能指数,对这些算法与传统的自适应信号处理算法进行比较。所得实验结果表明,独立分量分析算法在降噪上的效果优于自适应信号处理算法。因此在降噪上具有较大的应用价值。     

光电池非线性区PN结光生伏特效应的研究

根据光电池线性区应用叠加定理建立的PN结光生伏特效应理论，阐述了PN结光生伏特效应在光电池非线性区的应用。     

预应力混凝土连续梁的非线性分析

采用分层法对预应力混凝土梁进行了非线性有限元分析，利用计算机数值计算方法，模拟预应力混凝土多跨连续梁的加载试验全过程，分析预应力混凝土梁的非线性特性，通过各层单元引入对应材料的非线性模型，并采用离散裂缝模型，能较正确地模拟预应力混凝土梁从弹性状态到极限状态的受力特性，算例表明该方法既能使混凝土非线性分析的结构模型得到简化，又能较好地预测预应力混凝土梁的开裂荷载、极限荷载、正截面裂缝开展、荷载挠度曲线关系和钢筋及混凝土的应力变化过程，计算结果与试验结果吻合较好。