基于权的最小平方法的山区道路交通安全度模糊综合评价

针对山区道路交通特点,综合考虑影响山区道路交通安全度的人、车、路、环境等主要因素,运用层析分析法构建道路交通安全度评价指标体系,基于权的最小平方法建立模糊综合评价模型,并利用加权平均原则对其进行综合评价.以云南省罗富路"者桑"段为例,结果表明该模型可以有效的反映道路的安全状况,且权的最小平方法可以实现道路交通安全度主要影响因素权重系数的精确分配,合理反映各评价指标的重要性,为提高道路的交通安全性奠定基础.     

A practicable way for computing the directional derivative of the optimal value function in convex programming

Formulas for computing the directional derivative of the optimal value function or of lower or upper bounds of it are well-known from literature. Because they have as a rule a minmax structure, methods from nondifferentiable optimization are required.

Considering a fully parametrized convex problem, in the paper the mentioned minmax formulas are transformed into usual programming problems. Although they are nonconvex in general, the computational effort is much lower than that for minmax problems. In several special cases, for instance, for linear least squares problems, linear programming problems arise.     

Comprehensive data analysis of femtosecond transient absorption spectra: A review

Nowadays, time-resolved spectroscopy data can be routinely and accurately collected in UV-vis femtosecond transient absorption spectroscopy. However, the data analysis strategy and the postulation of a physically valid model for this kind of measurements may be tackled with many different approaches ranging from pure soft-modeling (model-free) to hard-modeling, where the elaboration of a parametric spectro-temporal model may be required. This paper reviews methods that are used in practice for the analysis of femtosecond transient absorption spectroscopy data. Model-based methods, common in photochemistry, are revisited, and soft-modeling methods, which originate from the chemometrics field and that recently disseminated in the photo(bio)chemistry literature, are presented. These soft-modeling methods are designed to suit the intrinsic nature of the multivariate (or multi-way) measurement. Soft-modeling tools do not require a priori physical or mechanistic models to provide a decomposition of the data on the time and wavelength dimensions, the only requirement being that these two (or more) dimensions are separable. Additionally, Bayesian data analysis, which provides a probabilistic framework for data analysis, is considered in detail, since it allows uncertainty quantification and validation of the model selection step.     

基于抗差估计的全姿态多位置寻北

为解决寻北过程中需要人工调平而耗时较长的问题,结合全姿态多位置寻北模型,采用总体最小二乘法估算北向角。该算法将陀螺漂移转化为测量误差,而转台倾斜误差、轴系误差及安装误差等同系数矩阵误差,在忽略较少误差项的同时完成寻北过程;并根据实际数据中含有粗差的情况,提出抗差总体最小二乘方法,引入 等价权函数消除粗差数据的影响,从而提高算法在含有粗差数据时的寻北精度。仿真数据分析和实验结果表明：该算法能有效削弱粗差对寻北精度的影响,实现全姿态高精度寻北。     

债务期限和资本结构的联合影响因素:一个结构方程模型

在考虑债务期限与资本结构相互依赖关系下,通过构建结构方程模型,采用中国上市公司面板数据,应用2SLS对债务期限和资本结构的联合影响因素进行经验检查,以拓展先前研究。研究发现,债务期限与资本结构是联立决定的,债务水平高的公司具有更多的长期债务,同时,长期债务多的公司具有更高的债务水平。     

正交对角拉丁方的构造

对角拉丁方是主对角线和反对角线均为截态的拉丁方。本文推广了朱烈［１］中关于正交对角拉丁方的主要构作。作为这些构作的应用，作者改进了Ｗａｌｌｉｓ和朱烈［１，２］中关于正交对角拉丁方的结果。     

对DW检验法的补充和改进

自相关检验是回归分析的一项重要内容，ＤＷ检验法又是自相关检验的最常用方法。但是，我国现有教科书中所介绍的ＤＷ检验都存在两个不确定的区间。对于这两个区间内的自相关如何判定，一直为我国学者所忽视。本文则是针对这一问题，特介绍一种方法，以解决之。     

修正阻尼最小二乘法在确定脑血流量系数中的应用

本文运用修正阻尼最小二乘法,通过以测定局部脑血流量的试验数据进行数据拟合建立双指数型数学模型 不仅确定了脑血流量系数α的估计值,而且确定了所有模型参数的满意估计。     

利用数据分组优化度量误差模型的参数估计

在一般的线性回归模型中,自变量都被认为是没有误差的准确值。然而当所有观测变量都可能存在误差时,通常的统计方法就会产生偏差。本文利用数据分组的思想,提出分组最小二乘估计法进行参数估计,减少了参数估计的偏差。并且在只知道误差界的情况下,利用分组最小二乘能给出几种度量误差模型的相合估计。     

非参数可加回归模型和非线性协整检验

本文基于非参数可加回归模型的局部核权最小二乘法提出变量间非线性协整的一种非参数检验方法。