协方差矩阵扰动生长曲线模型岭估计的影响分析

本文研究了协方差矩阵发生扰动时，生长曲线模型岭估计的影响分析，建立了生长曲线模型、协方差矩阵扰动生长曲线模型岭估计之间的关系式。讨论了协方差扰动和数据删除对岭估计的影响，导出了度量影响大小的基于岭估计的广义Cook距离Di^*（k）最后，用实例说明了用Di^*(k）度量生长曲线模型的影响点是有效的。     

增加试验数据对岭估计的均方误差的影响

在线性模型中,对于回归系数的岭估计和广义岭估计,本文给出了选择岭参数的条件,在此条件下,岭估计和广义岭估计不仅能改善LS估计,而且增加试验数据时,它们的均方误差都会减少。同时,本文将增加试验数据换成增加附加信息,从而讨论了附加信息对混合岭估计和混合广义岭估计的影响问题。     

多元协方差阵扰动模型岭估计的影响分析

本文研究了多元线性同归模型岭估计的影响分析问题.利用最小二乘估计方法,获得了多元协方差阵扰动模型与原模型参数阵之间的岭估计的一些关系式,给出了度量影响大小的基于岭估计的广义Cook距离.     

基于泛岭估计对岭估计过度压缩的改进方法

岭估计是解决多元线性回归多重共线性问题的有效方法,是有偏的压缩估计。与普通最小二乘估计相比,岭估计可以降低参数估计的均方误差,但是却增大残差平方和,拟合效果变差。本文提出一种基于泛岭估计对岭估计过度压缩的改进方法,可以改进岭估计的拟合效果,减小岭估计残差平方和的增加幅度。     

几种有偏估计的局部影响分析

本文首次从后验分布对数似然函数出发，对岭估计，广义岭估计和Ｓｔｅｉｎ估计进行局部影响分析，求出了它们在方差加权，均值漂移和自变量扰动等动等情况下的影响曲率和单参数的最大影响曲率及最大曲率方向。     

二阶随机控制变点的Kolmogrov型检验和估计

基于Kolmogrov型统计量和Kiefer过程,对一样本情形,我们讨论了二阶随机控制变点的检验和估计到了检验统计量的渐近分布且用模拟方法给出了其有限样本的分位数,并证明了变点的估计为强相合的。     

回归系数的综合岭估计

本文提出了回归系数的一种新的有偏估计－－综合岭估计，讨论了综合岭估计的优良性，可容许怀等性质，给出了其迭代和极小均方程误差的无偏估计解，在综合估计下，岭估计和根方估计作为其特例，从而统一了岭估计和根方估计理论。     

混合系数线性模型的几乎无偏岭估计

本文研究了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.利用岭估计方法得到了该模型的几乎无偏岭估计,并证明了在均方误差意义下,几乎无偏岭估计优于岭估计.最后讨论了有偏参数的选取问题.     

广义岭型主相关估计的方差最优性

本文在回归系数的岭型主相关估计的基础上,提出了广义岭型主相关估计,进一步研究其在降维估计类中方差最优性。     

岭估计优于最小二乘估计的条件

本文讨论在均方误差意义下岭估计优于最小二乘估计的问题，给出了岭估计优于小最小二乘估计的必要条件及较一般的充分条件。     

随机波动模型的局部影响分析

在期权定价问题中,有一类反映隐性不可观测波动的时间序列—随机波动(SV)模型.在一定条件下对其序列影响点进行识别:对SV模型的参数应用伪极大似然估计方法进行估计,并在此基础上应用Cook的局部影响分析方法,对其强影响点进行识别,并通过模拟实例,对其影响点识别的效果进行说明.     

Impact Assessment for Fuzzy Linear Regression Model Based on Case Deletion

Least squares method based on Euclidean distance and Lebesgue distance between fuzzy data is used to study parameter estimation of fuzzy linear regression model based on case deletion respectively. And the parameter estimations on two kinds of distance are compared. The input of the above model is real data and output is fuzzy data. The statistical diagnosis --- estimation standard error of regression equations is constructed to test highly influential point or outlier in observation data. At last through identifying highly influential point or outlier in actual data, it shows that the statistic constructed in this paper is effective.     

On the Approximation of Bounded Functions with Discontinuities of the First Kind by Generalized Shepard Operators

The authors investigate the approximation of bounded functions with discontinuities of the first kind by generalized Shepard operators. Estimate for the rate of convergence at a continuity point is obtained, while at the points of discontinuity it is shown that the sequence of generalized Shepard operators is almost always divergent. It is also shown that the sequence of Cesàro means of generalized Shepard operators is convergent everywhere for bounded functions which have only discontinuities of the first kind in [0,1].     

On the GLY Conjecture of upper estimate of positive integral points in real right-angled simplices

The GLY (Granville-Lin-Yau) Conjecture is a generalization of Lin, Xu and Yau's results. An important application of GLY is its use in characterizing an affine hypersurface in Cn as a cone over a nonsingular projective variety. In addition, the Rough Upper Estimate Conjecture in GLY, recently proved by Yau and Zhang, implies the Durfee Conjecture in singularity theory. This paper develops a unified approach to prove the Sharp Upper Estimate Conjecture for general n. Using this unified approach, we prove that the Sharp Upper Estimate Conjecture is true for n=4,5,6. After giving a counter-example to show that the Sharp Upper Estimate Conjecture is not true for n=7, we propose a Modified GLY Conjecture. For each fixed n, our unified approach can be used to prove this Modified GLY Conjecture.     

一般混合线性模型固定效应、随机效应与另一随机向量的联合估计

讨论一般混合线性模型中固定效应β、随机效应ξ_i(i=1,2,…,k)与另一随机向量δ的联合估计,得到了β、ξ_i(i=1,2,…,k)及δ的线性组合的最佳线性无偏估计,推广了有关文献中的结果,并从一个直观角度刻划了β、ξ_i(i=1,2,…,k)与δ的线性组合的最佳线性无偏估计的一种最优性,推广有关文献的结果.     

作物垄作的数学模型

应用高等数学中对面积的曲面积分等方法,建立了垄作种植中半椭圆形、抛物线型和三角形垄的数学模型,比较了不同垄形、垄宽、垄高在增加单位土地表面积和突出地面垄体体积的效果.     

Transformation of variables and the condition number in ridge estimation

Ridge estimation (RE) is an alternative method to ordinary least squares (OLS) estimation when collinearity is detected in a linear regression model. After applying RE, it is sensible to determine whether such collinearity has been mitigated. The condition number (CN) is a commonly applied measure to detect the presence of collinearity in econometric models, but to the best of our knowledge, it has not been extended to be applied after RE. In OLS estimation, Belsley et al. (Regression diagnostics: identifying influential data and sources of collinearity, Wiley, New York, 1980) established that the regressors must be of unit length and not centered to correctly calculate the CN. This paper reviews this requirement in the context of RE and presents an expression to calculate the CN in RE.     

Case influence diagnostics in the kaplan-meier estimator and the log-rank test

One or few observations can be highly influential on the Kaplan-Meier estimator, and consequently on the log-rank test statistic in comparing two survival functions. In this paper we derive case influence diagnostics for the Kaplan-Meier estimator and the log-rank test. We note that diagnostics in this context is quite different from the regression context where observations are usually assumed to be independent. Simulation studies are done to present some guidelines to determine influential observations deserving special attention. Illustrative examples are also given.     

Local influence on the goodness-of-fit test statistic in maximum likelihood factor analysis

The influence of observations on the goodness-of-fit test in maximum likelihood factor analysis is investigated by using the local influence method. Under an appropriate perturbation the test statistic forms a surface. One of main diagnostics is the maximum slope of the perturbed surface, the other is the direction vector corresponding to the curvature. These influence measures provide the information about jointly influential observations as well as individually influential observations.