半参数回归模型中二阶段估计的渐近性质

给定半参数回归模型Y＝X′β g(T) e,其中β∈R^p是未知参数向量,g(t)是定义在[0,1]上的未知函数,e是随机误差,本文研究了β,,g(t)和σ2的估计量βn,gn(t)和σn^2,在适当的条件下证明了它们的渐近正态性,并给出了gn(t)的最优收敛速度。     

半参数回归模型的渐近有效L-估计

对半参数回归模型yi=χiTβ+g(χi)+ei,i=1,2,…,n,对非参数函数g(·)采用核估计的方法,构造了参数向量β的L-估计量λn,在一些正则条件下,获得了λn的渐近正态性和非参数函数g(·)的估计量gn(t)的最优收敛速度可达到O(n-(1/3)),并且给出了标准化L估计量λn的渐近分布的Berry-Esseen界.     

纵向数据下半参数回归模型估计的渐近性质

本文考虑纵向数据下半参数回归模型: $y_{ij}=x_{ij}'\beta+g(t_{ij})+e_ij},\;i=1,\cdots,m,\;j=1,\cdots,n_i$. 基于最小二乘法和一般的非参数权函数方法给出了模型中参数$\beta$和回归函数$g(\cdot)$的估计, 并在适当条件下证明了$\beta$估计量的渐近正态性和$g(\cdot)$估计量的最优收敛速度\bd 模拟结果表明我们的估计方法在有限样本情形有良好的效果     

一个半参数回归模型的渐近正态性

考虑半多数回归模型yi＝xiβ＋g（xi）＋εi，lin，这里xi是具有已知方差σ的独立同分布随机样本，εi是具有零均值和有限方基σ2的独立同分布随机误差．β，g和εi的分布密度是未知的．本文作者构造了一个具有更小渐近方差的β的一个渐近正态估计．     

一类半参数回归模型的估计理论

考虑半参数回归模型Y=X’β+g(T)+e,其中(X,T)为取值于R^p×[0,1]上的随机向量,β为p×1未知参数向量,g为定义于[0,1]上的未知函数,e为随机误差,Ee=0,Ee²=σ²>0,且(X,T)与e独立。本文综合最近邻和最小二乘的方法定义了β,g和σ²的估计量,g_n^*和。在适当条件下证明了和的渐近正态性,并得到了g_n^*的最优收敛速度。     

一个半参数模型渐近有效估计的构造

对半参数回归模型Ｙ＝ＸＴβ十ｇ（Ｔ）＋ε，分别在ε的密度函数已知、未知的情况下，构造出了β的渐近有效估计．     

Ψ-混合异方差误差下半参数回归模型的加权小波估计

考虑半参数回归模型yi=xiβ+g(ti)+σiei, i=1,2,…,n,其中(zi,ti,ui)是固定设计点列,ei为Ψ-混合随机误差.用小波估计方法得到了参数,非参数及误差方差的加权小波估计量.在相当一般的条件下,得到了这些小波估计量的渐近正态性及弱收敛速度.     

半参数回归模型的估计的渐近性质

考虑半参数回归模型ｙｉ＝ｘｉ＾１β＋ｇ（ｔｉ）＋ｅｉ,１≤ｉ≤ｎ;其中ｇ为Ｒ上未知函数,σ０＾２＝Ｄ（ｅ１）柴根象等在１９９５年给出了β的二阶段估计βｎ,本文基于β１建立了σ０＾２的估计量σｎ＾２,研究了误差方差估计σｎ＾２的渐近正态性和强相合性,并且得到了可直接用于统计推断的统计量及其分布。     

污染数据半参数回归模型估计的渐近正态性

考虑半参数回归模型：ｙｉ＝ ｘｉβ＋ ｇ（ｔｉ）＋ ｅｉ,ｉ＝ １,２,…,ｎ．其中 Ｅｅｉ＝ ０, Ｅｅ２ｉ＝ σ２１ ＞ ０．假定ｙ１,ｙ２,…,ｙｎ 受到另一独立同分布随机变量序列 μ１,μ２,…,μｎ 的污染,｛μｉ｝与｛ｙｉ｝独立,且仅能观察到污染数据．文［１］对由污染数据作出的参数 β的估计 βｎ,证明了它的强相合性,而本文则证明了它的渐近正态性     

随机删失下半参数回归模型的估计理论

本文研究了随机右删失情形下半参数回归模型中未知参数的估计问题,证明了它们的渐近正态性．文中结果是完全数据情形下相应结果的推广和改进     

一类半参数回归模型的估计问题

该文对半参数回归模型ｙｉ~（Ｔ）＝βｘｉ~（Ｔ）＋ｇ（ｔｉ~（Ｔ））＋ε_ｉ~（Ｔ）,定义了β,ｇ的估计量β_Ｔ,ｇ_Ｔ（ｔ）,获得了它们的强相合、强一致相合、ｓ阶矩相合,ｓ阶一致矩相合性．     

部分线性模型中的Edgeworth展开

本文在相当一般的条件下，首先给出了部分线性模型中有关参数β的标准化统计量的一阶Ｅｄｇｅｗｏｒｔｈ展开，然后构造了误差方差的一个非残差型相合估计，最后给出了相应的学生化统计量的Ｅｄｇｅｗｏｒｔｈ展开．     

One-Term Edgeworth Expansion for Finite Population U-Statistics of Degree Two

By means of Hoeffding"s decomposition, we represent a finite population U-statistic of degree two by the sum of a linear and a quadratic part. Assuming that the linear part is nondegenerate, we prove the validity of one-term Edgeworth expansion for the distribution function of the statistic under the optimal (minimal) conditions on the linear part and 2 + moment condition on the quadratic part. No condition is imposed on the ratio N / n, where N, respectively n, denotes the sample size respectively the population size.     

一个有效估计:半参数非时齐扩散模型的局部线性复合分位回归估计

主要研究半参数非时齐扩散模型的参数估计问题.基于非时齐扩散模型的离散观测样本,首先得到漂移参数的局部线性复合分位回归估计,并证明估计量的渐近偏差、渐近方差和渐近正态性.其次,讨论了带宽的选择和局部线性复合分位回归估计关于局部线性最小二乘估计的渐近相对效,所得到的局部估计较局部线性最小二乘估计更为有效.最后,通过模拟说明了局部线性复合分位回归估计比局部线性最小二乘估计的模拟效果更好.     

Empirical Edgeworth Expansion for Finite Population Statistics. II

For symmetric asymptotically linear statistics based on simple random samples, we construct a one–term empirical Edgeworth expansion, where the moments defining the true Edgeworth expansion are replaced by their jackknife estimators. In order to establish the validity of the empirical Edgeworth expansion (in probability) we prove the consistency of the jackknife estimators.     

Edgeworth Expansion of Densities of Order Statistics with Fixed Rank

We give an Edgeworth expansion for densities of order statistics with fixed rank k.The Edgeworth expansion for densities of extreme values is then obtained as a special case k=1.     

Asymptotic Normality of LS Estimate in Simple Linear EV Regression Model

Though EV model is theoretically more appropriate for applications in which measurement errors exist, people are still more inclined to use the ordinary regression models and the traditional LS method owing to the difficulties of statistical inference and computation. So it is meaningful to study the performance of LS estimate in EV model. In this article we obtain general conditions guaranteeing the asymptotic normality of the estimates of regression coefficients in the linear EV model. It is noticeable that the result is in some way different from the corresponding result in the ordinary regression model.     

Edgeworth expansion of the Studentized product-limit estimator for truncated and censored data

Based on random left truncated and right censored data we investigate the one-term Edgeworth expansion for the Studentized product-limit estimator, and show that the Edgeworth expansion is close to the exact distribution of the Studentized product-limit estimator with a remainder of On(su-1/2).     

Edgeworth expansion in partial linear models

In this paper, under some fairly general conditions, a first-order Edgeworth expansion for the standardized statistic of β in partial linear models is given, then a non-residual type of consistent estimation for the error variance is constructed, and finally an Edgeworth expansion for the corresponding studentized version is presented.