最小二乘估计关于误差分布的稳健性

对于设计矩阵$X$是列降秩的线性统计模型, 本文讨论了最小二乘估计关于误差分布的稳健性, 给出了误差分布的最大类, 使得误差项的分布在此范围内变动时, 最小二乘估计在均方误差矩阵准则下是最优估计.     

Gauss-Markov估计关于误差分布的稳健性

对于一般线性模型y=Xβ+ε,本文讨论了在广义均方误差准则及均方误差矩阵准则下,未知参数β的可估函数Xβ的Gauss-Markov估计关于误差分布的稳健性,分别给出了误差项ε的最大分布类,使得误差项ε的分布在此范围内变动时,Gauss-Markov估计在相应准则下是最优估计.     

线性模型中F-检验的稳健性

本文讨论了一般线性模型中关于均值参数β的线性假设基于广义最小二乘估计的F-检验统计量的稳健性问题.主要研究了当误差的协方差矩阵含有参数时,设计阵可以列降秩情况下的F-检验统计量的稳健性,得到了F(V(θ))为该假设下F-检验统计量的误差协方差矩阵的最大类.并讨论了分块线性模型中,关于分块参数的线性假设的F-检验统计量的稳健性.     

带有异方差的部分线性回归模型的B样条估计

考虑一带有异方差的固定设计部分线性回归模型yij=x'ijβ+g(tij)+εij,i=1,2,…,k,j=1,2,…,ni,和∑ni=n,其中yij为响应变量,β=(β1,…,βp)'是未知的参数向量,g(.)是未知的函数,xij=(xij1,…,xijp)'和tij∈[0,1]为已知的非随机设计点,εij为均值0,方差是σ2i的随机误差,其中σ2i可能不同.通过B样条级数近似非参数分量,构造了参数分量β的一个半参数广义最小二乘估计.在一些矩条件下,导出了此半参数广义最小二乘估计的渐近分布,大多数在实际中遇到的误差分布都满足这些矩条件.另外,也构造了半参数广义最小二乘估计的渐近协方差矩阵的一个相合估计,还讨论了非参数分量的B样条估计.所有这些大样本性质都是在k趋于无穷大,n.有限时导出的.这些结果能被用来做渐近有效的统计推导.     

一类线性模型中Bayes估计的优良性

本文研究了一类线性模型中参数的Bayes线性无偏估计的优良性.利用矩阵论的相关知识,分别在平衡损失准则和均方误差阵准则下,得到了Bayes线性无偏估计优于广义最小二乘估计的条件.     

多元广义岭估计及K值选以的Q（c）准则

当自变量间存在复共线性时，最小二乘估计就表现出不稳定并可能导致错误的结果。本采用广义岭估计β（K）来估计多元线性模型的回归系数β=vec(B),通过岭参数K值的选取 ，可使广义岭估计的均方误差MSE小于最小二乘估计的MSE。指出了广义岭估计中根据MSE准则选取K值存在的主要缺陷，采用了一种选取K值的新准则Q（c），它包含MSE准则和最小二乘LS准则作为特例，从理论上证明和讨论了Q（c）准则的优良性，阐明了c值的统计 含义，并给出了确定c值的方法。     

带有异方差的部分线性回归模型的B样条估计

考虑一带有异方差的固定设计部分线性回归模型yij=X'ijβ+g(tij)+εij,i=1,2…,k:j=1,2,…,ni,和sum from i=1 to kni=n,其中yij为响应变量,β=(β1,…,βp)’是未知的参数向量,g(·)是未知的函数,Xij=(Xij1,…,Xijp)’和tij∈[0,1]为已知的非随机设计点,εij为均值0,方差是σi2的随机误差,其中σi2可能不同.通过B样条级数近似非参数分量,构造了参数分量β的一个半参数广义最小二乘估计.在一些矩条件下,导出了此半参数广义最小二乘估计的渐近分布,大多数在实际中遇到的误差分布都满足这些矩条件.另外,也构造了半参数广义最小二乘估计的渐近协方差矩阵的一个相合估计,还讨论了非参数分量的B样条估计.所有这些大样本性质都是在k趋于无穷大,ni有限时导出的.这些结果能被用来做渐近有效的统计推导.     

推广的生长曲线模型中未知参数矩阵的广义最小二乘估计的可容许性

本文在设计矩阵与结构矩阵分别正交的条件下,研究了推广的生长曲线模型未知参数矩阵的广义最小二乘估计.运用矩阵理论证明了此广义最小二乘估计在某个线性估计类中的可容许性.并对潘建新(1989)的结果的推广.     

协方差阵估计的比较

本文在一般线性回归模型误差异方差情况下，通过计算机模拟对回归系数最小二乘估计的协方差矩阵的估计进行了比较。结果表明，当样本大小大于50时，回归系数的最小二乘估计具有较高的估计精度；其协方差矩阵的五种估计以普通最小二乘估计的协方差矩阵为最优。     

混合系数线性模型参数的广义Liu估计

本文研究连续测量数据情况下的混合系数线性模型的参数估计问题.利用压缩估计方法给出了该模型的一类新的有偏估计-广义Liu估计,并在均方误差意义下,证明此类估计分别优于最小二乘估计、Liu估计.最后讨论参数的选取问题.     

Representations of Nature of Science in Selected Histories of Science in the Integrated Science Textbooks in China

This study aimed to examine the representations of nature of science (NOS) in the eight histories of science selected from three series of integrated science textbooks used in junior high school in China. Ten aspects of NOS were adopted in the analytical framework. It was found that NOS had not been well treated in the selected histories of science in the three series of science textbooks. Specifically, it was found that the empirical and inferential aspects were treated better than other aspects, and discrepancies existed among the three series of science textbooks and among the eight histories of science in terms of dealing with the target NOS aspects. Implications for addressing NOS in historical materials in science textbooks were discussed in the final part of this paper.     

Existence of equilibria in articulated bearings in presence of cavity

The existence of equilibrium solutions for a lubricated system consisting of an articulated body sliding over a flat plate is considered. Here we consider the case when cavity can occur.     

FANN模型在金属矿冲击地压预测中的应用

金属矿山冲击地压是采矿工程中所涉及到的重大灾害之一.冲击地压的发生是由多方面因素造成的,具有动态和模糊性,在客观上属于一个复杂的非线性动力学过程,这使得冲击地压预测系统的数据处理不能按照常规的线性系统法进行处理.根据模糊神经网络理论,本文给出了多源信息融合的模糊人工神经网络(FANN)模型.通过具体工程应用,说明了本文分析模型的正确性和有效性.     

Reasoning about variation in the intensity of change in covarying quantities involved in rate of change

This paper extends work in the area of quantitative reasoning related to rate of change by investigating numerical and nonnumerical reasoning about covarying quantities involved in rate of change via tasks involving multiple representations of covarying quantities. The findings suggest that by systematically varying one quantity, an individual could simultaneously attend to variation in the intensity of change in a quantity indicating a relationship between covarying quantities. The results document how a secondary student, prior to formal instruction in calculus, reasoned numerically and nonnumerically about covarying quantities involved in rate of change in a way that was mathematically powerful and yet not ratio-based. I discuss how coordinating covariational and transformational reasoning supports attending to variation in the intensity of change in quantities involved in rate of change.     

ARIMA模型在新疆巴州梅毒疫情预测中的应用

搜集2008-2014年新疆巴音郭楞蒙古自治州(简称巴州)梅毒月发病数据,采用时间序列分解方法(Time Series Decomposition methods)探讨该地区梅毒月发病率的季节性,建立ARIMA(0,1,1)(1,0,1)_(12)时间序列模型,模型预测值的动态趋势与实际发病率基本吻合,平均绝对百分比误差MAPE=17.36,具有较高的预测精度,可以较好的预测短期内梅毒的变化趋势,为梅毒的预防控制措施提供可靠依据.     

Centers of symmetry in finite intersections of balls in Banach spaces

It is proved that a real Banach spaceX is aG-space (C _σ - space)if and only if the non-empty intersection of three balls with equal radii (any three balls) has a center of symmetry.     

Distribution of Magnetization in the Vicinity of Point Defects in Ferromagnetics

The localized distributions of magnetization, which slowly decrease with distance in the vicinity of magnetic imperfections in homogeneously magnetized ferromagnetics, were calculated in this work. It is shown that, in the case of the slowest decrease with distance, such distributions of magnetization interact with the domain wall, according to a formula that differs from that for the energy of the interaction between the homogeneous magnetic defect and the domain wall. The potential of the interaction between such imperfections was obtained.