查询词典 exponential family

This paper studies the relationship between the approximate confidence and the statistical curvature in nonlinear exponential family regression models with linear restriction from geometric point of view.

本文从几何的观点，研究了带有线性约束的指数族非线性回归模型下参数的近似置信域与统计模型曲率之间的一般联系，获得了参数的近似置信域。

The objective of this paper is to estimate the parameters of generalized exponential family ARMA models and construct the confidence intervals of the parameters. In this paper we divided the problem into continuous type situation and discrete type situation.

本文针对广义指数族ARMA模型，分为连续型指数族和离散型指数族两种情况讨论模型的参数估计，并运用不同的Bootstrap方法构造参数的置信区间和置信带。

The early references include -[5], which are based on the linear models or generalized linear models; on the other hand, [6]-[10] are those based on the nonlinear models which are more practical. But they are all restricted in the exponential family of distributions. That will not practice in most of the trials. Although being the most flexible among them, the estimation methods in [1] has many disadvantages for requiring the model to be generalized linear. Based on [1], this paper extended the method to the generalized nonlinear model.

较早的如[1]-[5]，他们都是基于线性或广义线性模型进行分析研究；而基于更为实用的非线性模型的研究则有：[6]-[10]等，他们大多由于模型要求数据属于指数分布族或者模型假定为线性模型，这都限制了模型的实用性，其中以[1]所提的一系列广义线性估计方程实用范围较广，但其模型中要求的广义线性模型还是具有一定的局限性。

Likelihood inference will be developed using the exponential family of distributions. Extensions to quasi-likelihood methods will also be discussed, which allow the relaxation of some model assumptions.

运用指数族分布发展似然推断，还将讨论允许放松一些模型假设的准似然方法的扩展。

Exponential family of distributions...

大家庭尤指三代以上同堂者

By using the kernel-type density estimation in the case of identically distributed and negatively associated samples, the empirical Bayes test rules for the scale exponential family are constructed, and the asymptotically optimal property is obtained.

本文利用同分布负相协样本情形概率密度函数的核估计构造了刻度指数族参数的经验Bayes检验函数，并获得了它的渐近最优

We definite and study the very extensive nonlinear random effect models, i. e. exponential family nonlinear models with random effect, then we employ the Laplace methods to deal with these models. Based on this method, the fixed effect parameter estimates and Gauss-Newton formula are obtained. Some asymptotic properties of estimate are proved under some mild assumptions.

首次定义并研究了一类非常广泛的非线性随机效应模型-指数族非线性随机效应模型，并应用Laplace展开方法，给出该模型中固定效应参数的估计以及Gauss Netown选代算法，同时讨论了参数估计的渐近性质。

For separable and continous exponential family models (such as normal, gamma, and inverse Gaussian models), this paper discusses the tests for departures from nominal dispersion in the framework of longitudinal nonlinear models with varying dispersion and/or random effects. The score test statistics are constructed and their asymptotic distributions and local powers are derived.

本文针对可分的连续型指数族回归模型（如正态模型，Γ模型，逆高斯模型），讨论广义非线性纵向数据模型中偏离名义离差的检验问题，得到了检验的score统计量，并推导了它们的渐近分布和局部近似功效。

Results: GLMMs allow the index may be one of the exponential family (Contimuum distributions including Nomal ,beta distribution ,chisquared distribution etc;Disperse distributions including Binomal ,Poisson and inverse Binomal etc), the vecor of expected means of the index is linked to the model parameters by a link function and model the linear equation, simple the calculator procedure.

结果： 广义线性混合效应模型允许临床疗效评价指标是指数家族中任意分布（如：连续分布包括正态分布、beta分布、卡方分布等；离散分布包括二项分布、泊松分布、负二项分布等），可以通过连接函数将疗效指标的均数向量与模型参数建立线性关系，简化运算过程。

This dissertation investigates the construction of pseudo-random sequences (pseudo-random numbers) from elliptic curves and mainly analyzes their cryptographic properties by using exponential sums over rational points along elliptic curves. The main results are as follows:(1) The uniform distribution of the elliptic curve linear congruential generator is discussed and the lower bound of its nonlinear complexity is given.(2) Two large families of binary sequences are constructed from elliptic curves. The well distribution measure and the correlation measure of order k of the resulting sequences are studied. The results indicate that they are "good" binary sequences which give a positive answer to a conjecture proposed by Goubin et al.(3) A kind of binary sequences from an elliptic curve and its twisted curves over a prime field F_p. The length of the sequences is 4p. The "1" and "0" occur almost the same times. The linear complexity is at least one-fourth the period.(4) The exponential sums over rational points along elliptic curves over ring Z_ are estimated and are used to estimate the well distribution measure and the correlation measure of order k of a family of binary sequences from elliptic curves over ring Z_.(5) The correlation of the elliptic curve power number generator is given. It is proved that the sequences produced by the elliptic curve quadratic generator are asymptotically uniformly distributed.(6) The uniform distribution of the elliptic curve subset sum generator is considered.(7) We apply the linear feedback shift register over elliptic curves to produce sequences with long periods. The distribution and the linear complexity of the resulting sequences are also considered.

本文研究利用椭圆曲线构造的伪随机序列，主要利用有限域上椭圆曲线有理点群的指数和估计讨论椭圆曲线序列的密码性质——分布、相关性、线性复杂度等，得到如下主要结果：(1)系统讨论椭圆曲线-线性同余序列的一致分布性质，即该类序列是渐近一致分布的，并给出了它的非线性复杂度下界；(2)讨论两类由椭圆曲线构造的二元序列的"良性"分布与高阶相关性(correlation of order κ)，这两类序列具有"优"的密码性质，也正面回答了Goubin等提出的公开问题；(3)利用椭圆曲线及其挠曲线构造一类二元序列，其周期为4p(其中椭圆曲线定义在有限域F_p上)，0-1分布基本平衡，线性复杂度至少为周期的四分之一；(4)讨论了剩余类环Z_上的椭圆曲线的有理点的分布估计，并用于分析一类由剩余类环Z_上椭圆曲线构造的二元序列的伪随机性；(5)讨论椭圆曲线-幂生成器序列的相关性及椭圆曲线-二次生成器序列的一致分布；(6)讨论椭圆曲线-子集和序列的一致分布；(7)讨论椭圆曲线上的线性反馈移位寄存器序列的分布，线性复杂度等性质。

On the other hand, the more important thing is because the urban housing is a kind of heterogeneity products.

另一方面，更重要的是由于城市住房是一种异质性产品。

Climate histogram is the fall that collects place measure calm value, cent serves as cross axle for a few equal interval, the area that the frequency that the value appears according to place is accumulated and becomes will be determined inside each interval, discharge the graph that rise with post, also be called histogram.

气候直方图是将所收集的降水量测定值，分为几个相等的区间作为横轴，并将各区间内所测定值依所出现的次数累积而成的面积，用柱子排起来的图形，也叫做柱状图。