查询词典 covariance matrix

This thesis has mainly contributed two results in theory: one is that the covariance matrix is not positive definitive if the number of sampling is least than the number of variables, the other is that the covariance matrix of discrete sample is positive definitive if and only if the sum of every random column vector of data matrix is non I-linear combination.

本论文在理论上，主要得出两个新的结果：ⅰ抽样调查中，若样本的个数少于变量的个数则样本协方差矩阵恒为非正定；ⅱ离散型样本协方差矩阵正定的充要条件是样本资料阵的各随机列向量是非I-线性组合。

Studying the positive definitiveness of the covariance matrix from discrete data is important to design the sampling plan and provides the base for the data analysis.However, there have been few outcomes about the positive definitiveness of covariance matrix, most of which have been restricted to the Covariance-matrix of continuous sample.

研究离散型样本协方差矩阵的正定性有助于判断是否可以降低样本的维数，有利于优化抽样个数，为抽样调查的优化设计方案提供一定的理论基础；为基于特征根的多元统计分析提供理论指导。

Unlike the previous method, however, the proposed algorithm obtains the new transformed matrix by taking the conjugate operation to the forward and backward spatial smoothing covariance matrix of the received data, so that the modified covariance differencing matrix which is a Hermitian matrix of zero real part can lower the computation load effectively during the eigenvalue decomposition.

不同于以前的算法，提出的算法通过对接收数据的前后向空间平滑协方差矩阵进行共轭运算得到新的变换矩阵，因此修正后的协方差差分矩阵是个实部为零的厄米特矩阵，从而有效地降低了特征分解过程的计算量。

In order to reduce calculation error, the frequency distribution of average values is used to compute the mixed distribution's digital features of each component distribution, thereinto, the number of the component distribution is determined by AIC, choose the number that meets the minimum value of AIC as the component number of mixed distribution, and the other parameters are estimated by EM algorithm; Secondly, because each component distribution is corresponding to a kind of major gene genotype, according to the values of the average and variance of the each component distribution, we can use the limit error of the normal distribution to plot each individual into the correspondent component distribution, namely into correspondent major gene genotype. Then we regard each major gene genotype as a treatment level of one-way analysis of variances, and the one-way multivariate analysis of variance is carried out to calculate the covariance matrix of major gene effect, covariance matrix of polygene effect, covariance matrix of environment effect and so on; At last, combining the weights of the each component distribution of mixed distribution, we can calculate the variance of major gene effect, the variance of polygene effect, environmental variance and the genetic gain of the quantitative trait.

为减小计算误差，本研究采用均值的频数分布来计算各成分分布的数字特征，其中成分分布个数根据AIC准则，选择使AIC值达到最小的成分分布个数作为混合分布的成分分布数，分布中其它参数的确定利用EM算法来估计；其次，每个成分分布对应一种主基因基因型，根据各个成分分布的均值和方差，利用正态分布的极限误差将每个个体划分到相应的成分分布中，即相应的主基因基因型中，将每种主基因型作为单因素方差分析的一个处理水平，对其进行单因素的多元方差分析，分别计算主基因效应协方差阵、多基因效应协方差阵、环境协方差阵等参数；最后结合混合分布中各成分分布的权重即各主基因基因型的分离比例，计算主基因效应方差，多基因效应方差和环境方差，以及遗传力等参数，进而计算该数量性状的遗传进展。

First we construct a covariance matrix from sample images, then compute the eigenvalues and corresponding eigenvectors of the covariance matrix, construct a feature matrix with the eigenvectors. Then every images in database can be projected into the feature matrix and gain a projection vector, so does the input image. Then we can judge the resemblance between input image with each image in database by computing the distance between their projection vectors.

我们首先根据采集的样本图像构造一个协方差矩阵，然后求取该矩阵的特征值，以这些矩阵特征值对应的特征向量构造出一个特征空间，然后将输入图像向该特征空间映射，将获取的映射系数与样本库中图像的映射系数进行距离计算，根据计算出的距离判定输入图像与样本图像间的匹配程度。

Five ways on comparing covariance matrix are applied to the Shanghai 50 Indexes Stock Exchange, which are sample covariance matrix, scalar matrix, two-parameter covariance matrix, single index matrix, constant correlation matrix. We adopt principal components method and Markowitz portfolio method to measure stock market risk using VaR, getting the effect of measuring market risk. The result shows that sample covariance matrix and two-parameter covariance matrix could measure market risk more effectively.

本文以上证50指数数据为样本，采用样本协方差矩阵、数量矩阵、两参数模型矩阵、单指数模型矩阵、常量相关矩阵作为与股票相关的协方差矩阵，结合投资策略选择的主成分方法和Markowitz最优投资组合方法，计算VaR以度量市场风险，并比较了五种协方差矩阵度量市场风险的效果，结果表明，在主成分方法中，样本协方差矩阵和两参数矩阵方法能有效的度量市场风险。

Ects, the covariance matrix of observation vector has special structure,and using the linear transformation for original model by idempotent matricesin the spectral decomposition of the covariance matrix, the problem of estima-tion of the covariance matrix becomes simultaneous estimation of all the distincteigenvalues of it.

在带有随机回归系数的一般线性模型中，首次提出了随机回归系数和参数的Minimax估计问题，分别在齐次线性估计类和一切估计类中研究了一个线性估计的Minimax性。

On the ground that the covariance between the disturbing gravity field elements is not isotropic, the covariance matrix has a complicated structure (its submatrix being not repetitive Toeplitz matrix) and thus its degree cannot be degraded with transformation matrix method, so it cannot be put into practice. So far, the application of least squares collocation to the modeling and data processing of the horizontal disturbing gravity field observations has not been found in literature.

由于水平扰动场元之间的协方差并非各向同性，导致协方差矩阵结构复杂(子矩阵不是 Toeplitz 循环阵)，不能利用变换矩阵将其降阶，无法付诸实践，迄今尚无最小二乘配置理论应用于水平扰动场元观测量的模型化公式和数据处理方法。

The algorithms of MUSIC and ESPRIT are introduced, which are the most important algorithms in array signal processing. A method is proposed to make the estimation of the covariance matrix become Toeplitz matrix using the Toeplitz characteristic of covariance matrix.

第2章建立了阵列信号的模型，主要分析了两种无方向模糊的阵列：阵元数大于6的均匀圆阵和非均匀L形线性阵列，并讨论了非均匀L形线性阵列无模糊设计的方法；然后介绍了在阵列信号处理中，两种最主要的算法：MUSIC算法和ESPRIT算法。

After studying this phenomenon, the author finds that, the covariance matrix of the complex expressions of horizontal gradients of the disturbing gravity field elements has a structure of blockwise repetitive Toeplitz matrix, though the covariance within the disturbing gravity field elements is still anisotropic. Therefore, the collocation problem of the complex combination of horizontal components is similar to that of gravity anomaly, which makes the degradation be able to be completed by FFT transformation matrix.

作者研究发现，利用水平梯度的复组合，即复数表示后，扰动重力场元复组合之间的协方差函数尽管还是各向异性，但它们对应的协方差矩阵却具有分块 Toeplitz 循环阵的结构，因而水平分量复组合的配置问题与重力异常的配置问题相似，可以利用傅立叶变换矩阵进行降阶处理。

Neither the killing of Mr Zarqawi nor any breakthrough on the political front will stop the insurgency and the fratricidal murders in their tracks.

在对危险的南部地区访问时，他斥责什叶派民兵领导人对中央集权的挑衅行为。

In fact,I've got him on the satellite mobile right now.

实际上 我们已接通卫星可视电话了