参数估计

Using the result for non-restricted model, we transform the restricted model to common model, and multi collectivity model to single collectivity model, thus, the necessary and sufficient conditions that nonhomogeneous linear estimators for Sβ are admissible in the class of nonhomogeneous linear estimators are obtained which filled the blank for admissibility for restricted linear model.

对线性等式约束的共同均值线性模型，利用无约束单总体模型的现有结果，通过适当变换，把等式约束模型向无约束转换，并把多总体转换为单总体，在矩阵损失下找到了均值参数β的条件可估函数Sβ的线性估计∑mAiyi+a在非齐次线性估计类中可容许的充要条件，填补了等式约束的共同均值线性模型可容许性方i=1面的空白。

The paper studies the auto-covariance estimation of Gamma distribution by using the asymptotic behavior of student U -statistic,gives the large sample interval estimation for the scale parameter,and carries out the computing simulation according to the method of random simulation.

利用学生氏U－统计量的渐近性质，研究伽玛分布的自协方差估计，同时给出了尺度参数的大样本区间估计，并采用随机模拟的方法进行计算模拟

By detecting the autocorrelation of the sinusoid, the moments of arrival and ending of the ...

同时，通过对该正弦信号频率估计，结合已获得的到达时刻参数，就可以实现对该线性调频分量初始频率的估计。理论分析和计算机模拟结果表明本方法切实可行。

The main contents of this course include: the principles and methods of statistical modeling, the estimation, testing and diagnosis of linear regression model, the theories and analytic methods of time series model, robust estimation theory, a simple introduction of general model and non-parameter model.

本课程的内容有：统计建模的原理与方法、回归模型的估计与检验问题、线性回归模型的诊断分析、时间序列模型的理论与分析方法、稳健估计理论、广义模型与非参数模型简介。

This paper focus on some topics described as following based on the summarizer of:(1) Feature extraction of the EEGAnalyzing the origin, the mechanism and the framework of the EEG and using the power spectral density, AR model parameter, band power and the wavelet entropy as the features of the EEG recorded during imagination of hand movements.

本文在综述国内外研究现状的基础上对基于脑电信号的意识任务的识别进行了以下几个方面的研究讨论：(1)提取脑电信号的多个特征量对EEG信号的来源，产生机理，结构特征等进行分析，运用经典功率谱估计，AR模型功率谱估计，AR模型参数，信号能量，小波熵等多种方法对想象左右手动作的脑电信号进行特征提取，并比较其性能。

This algorithm can give consistent and reliable results for both steady state and transient performance sensitivity estimation.

既可以用于稳态性能测度的参数灵敏度估计，也可用于终止型性能测度的灵敏度估计。

The empirical Bayes estimation for parameters of the one-side truncated distribution family with convergence rate which can close to 1 arbitrarily is investigated using NA samples and an example that satisfies the conditions of theorem is given.

运用NA样本密度函数核估计构造了一类截断型分布族参数的经验Bayes估计，建立了它的收敛速度，证明了在适当条件下该收敛速度可以任意接近于1，文中还给出了适合定理条件的例子。

In this paper, total logistics amounts are chosen as evaluation index, and artificial time series are designed to solve the shortness of statistical data in Chinese logistics. Spectrum estimation theory depicts time characteristics in frequency domain thus has such benefit than time domain methods. This paper evaluates the period of Chinese logistics using spectrum estimation. Stationarity of artificial series is verified, parameter sensitivity of truncation point is analyzed, six periods with different delay window are compared, and significance of period evaluated is tested.

中国物流统计数据缺乏，客观上限制了对其周期规律的研究，本文选取社会物流总额作为测度指标，设计了一种人工序列，解决了统计数据过短问题；谱估计法从频域角度揭示客观事物的时间特性，在研究时间序列周期波动方面具有时域分析法所不具备的优势，作者采用谱估计法对中国物流发展周期进行测定，检验了指标序列平稳性，分析了截断点参数灵敏度，比较了6种不同滞后窗下周期值，并检验了所测得周期的显著性。

And usually this method will suffice to typify all the rest, and not only can we easily solve the problems of calculating statistics of mathematical statistics in this way, but also a large number of sophisticated data can be avoided in the mathematical statistics teaching.

在方差分析中，无论是单因素还是双因素分析，基本思想方法和基本概念都是很清楚的，学生在经过参数的区间估计、点估计和假设检验的学习之后，对这些概念的掌握应该是顺理成章的事。

According to this,the best linear unbiased estimate method of location-scale distribution for incomplete interval censored data is presented,the confidence l.

在此基础上，针对位置-尺度分布族提出一种不完全区间数据最佳线性无偏估计方法，得到了其百分位值的置信限估计，并对工程中常见的极值分布、两参数Weibull分布、正态分布进行了详细讨论。

For a big chunk of credit-card losses; the number of filings (and thus charge-off rates) would be rising again, whether

年美国个人破产法的一个改动使得破产登记急速下降，而后引起了信用卡大规模的亏损。

Eph. 4:23 And that you be renewed in the spirit of your mind

弗四23 而在你们心思的灵里得以更新