共查询到20条相似文献,搜索用时 296 毫秒
1.
2.
非参数回归函数估计的随机加权逼近 总被引:1,自引:0,他引:1
本文应用随机加权法的思想构造了回归函数的最近邻估计和核估计的随机加权统计量,并证明了用随机加权统计量的分布逼近两类估计量的分布之精度可达到o(n~(-1/2P),其中1<p ≤ 2. 相似文献
3.
Raoand Zhao(1992)提出了一种用随机加权的方法去逼近线性回归模型中M-估计的渐近分布。之前,Fang and zhao(2002)把这种方法推广到设计阵是随机的删失回归模型.本文,我们把这个结果推广到设计阵是非随机的删失回归模型,并证明该随机加权方法的一些大样本性质。 相似文献
4.
半参数回归模型中随机加权M估计的强逼近 总被引:4,自引:0,他引:4
用随机加权法给出了半参数回归模型中参数的随机加权M估计,在一般的条件下证明了用随机加权统计量的分布逼近原估计量误差的分布的强有效性,并给出了M估计的最优强收敛速度。 相似文献
5.
本文首先研究了条件密度函数近邻-核估计的误差分布的正态逼近精度,然后利用随机加权法构造了近邻-核估计的随机加权统计量,获得了随机加权逼近精度。 相似文献
6.
7.
王炳章 《高校应用数学学报(A辑)》1997,(2):157-162
研究了一种最近邻回归估计的分布逼近问题,利用随机加权法,给出了最近邻回归估计误差的逼近分布及其逼近的精度,从而改进了文献「1」的结论。 相似文献
8.
本文首先了条件密度函数近邻一核估计的误差分布的正态逼近精度,然后利用随机加权法构造了近邻-核估计的随机加权统计量,获得了随机加权逼近精度。 相似文献
9.
线性模型M估计分布的Bootstrap逼近的强收敛 总被引:2,自引:0,他引:2
本文讨论标准线性模型M估计分布的随机加权逼近,建立了随机加权M估计的线性表示及Bootstrap强逼近,同时还得到了逼近的一致强收敛速度,其主要部分的阶在Berry-Esseen意义下已达最优. 相似文献
10.
标准化样本均值分布的随机加权逼近—多维情形 总被引:3,自引:0,他引:3
本文考虑多维标准化样本均值分布的随机加权逼近,得到了O((?)~(-1/2))的最优精度,从而拓广了随机加权法的应用范围. 相似文献
11.
RANDOM WEIGHTING APPROXIMATION IN LINEAR REGRESSION MODELS 总被引:1,自引:0,他引:1
石坚 《应用数学学报(英文版)》1996,12(2):137-143
RANDOMWEIGHTINGAPPROXIMATIONINLINEARREGRESSIONMODELSSHIJIAN(DepartmentofProbabilityandStatistics,PekingUniversity,Beijing1008... 相似文献
12.
Xue Liugen Cai GuoliangDept.of Appl.Math. Beijing Polytechnic Univ. Beijing . Faculty of Science Jiangsu Univ.of Science Technology Zhenjiang . 《高校应用数学学报(英文版)》2000,(4)
§ 1 IntroductionLet(X,Y) be a random vector taking values Rp×Rqand assume that with given X=x,f(y|x) is the conditional density of Y,the Borel-measurable function on(x,y) ,X has amarginal distribution function F(x) and a marginal density function f(x) .Let(X1 ,Y1 ) ,...,(Xn,Yn) be i.i.d.sample taking values in(X,Y) .A class of double kernel esti-mates of f(y|x) proposed by Zhao Linchang and Liu Zhijun[1 ] has the formfn(y|x) = ni=1K1Xi -xan K2Yi -ybn bqn nj=1K1Xj-xan ,(1 .1 )where… 相似文献
13.
14.
Liu-genXue Li-xingZhu 《应用数学学报(英文版)》2005,21(2):295-302
In this paper, the L_1-norm estimators and the random weighted statistic for a semiparametric regression model are constructed, the strong convergence rates of estimators are obtain under certain conditions, the strong efficiency of the random weighting method is shown. A simulation study is conducted to compare the L_1-norm estimator with the least square estimator in term of approximate accuracy, and simulation results are given for comparison between the random weighting method and normal approximation method. 相似文献
15.
XueLiugen CaiGuoliang 《高校应用数学学报(英文版)》2000,15(4):425-432
In this paper, the normal approximation rate and the random weighting approximation rate of error distribution of the kernel estimator of conditional density function f(y!|x) are studied. The results may be used to construct the confidence interval of f(y|x). 相似文献
16.
In this paper, a strongly consistent estimation of the optimal trimming proportion in trimmed mean is found by the random weighting method. In addition, using the same method a strongly consistent estimation for the distribution of some adaptive estimator is also obtained.Supported by the NNSF of China and the Doctoral Foundation of the Institutions Higher Learning of China 相似文献
17.
本文提出方差分量ANOVA估计的一种改进方法, 证明了对于一般的方差分量模型, 只要方差分量的ANOVA估计存在就可以通过此方法给出其改进形式, 并且在均方误差意义下优于ANOVA估计. 特别地, 对于单向分类随机效应模型, Kelly和Mathew[1]对ANOVA估计的改进就是我们提出的改进方法的特殊形式, 这也给出了此类改进估计在均方误差意义下优于ANOVA估计的另一种合理的解释. 同时, 本文又将此思想应用到对谱分解估计的改进上. 本文应用协方差的简单性质证明了对带有一个随机效应的方差分量模型, 当随机效应的协方差阵只有一个非零特征值时, 随机效应方差分量谱分解估计在均方误差意义下总是优于ANOVA估计. 本文最后将第三节的结论推广到广义谱分解估计下, 同时给出广义谱分解估计待定系数的一个合理的取值. 相似文献
18.
本文考虑了严平稳随机序列密度函数的非线性小波估计,证明了在Besov空间中,非线性小波估计可达到最优收敛速度.进一步讨论了自适应非线性小波估计,证明了自适非线性小波估计可达到次最优速度即和最优速度相差in n. 相似文献
19.
Recently, Kundu and Gupta (Metrika, 48:83 C 97, 1998) established the asymptotic normality of the least squares estimators in the two dimensional cosine model. In this paper, we give the approximation to the general least squares estimators by using random weights which is called the Bayesian bootstrap or the random weighting method by Rubin (Annals of Statistics, 9:130 C 134, 1981) and Zheng (Acta Math. Appl. Sinica (in Chinese), 10(2): 247 C 253, 1987). A simulation study shows that this approximation works very well. 相似文献
20.
Statistical estimation in partial linear models with covariate data missing at random 总被引:1,自引:0,他引:1
Qi-Hua Wang 《Annals of the Institute of Statistical Mathematics》2009,61(1):47-84
In this paper, we consider the partial linear model with the covariables missing at random. A model calibration approach and
a weighting approach are developed to define the estimators of the parametric and nonparametric parts in the partial linear
model, respectively. It is shown that the estimators for the parametric part are asymptotically normal and the estimators
of g(·) converge to g(·) with an optimal convergent rate. Also, a comparison between the proposed estimators and the complete case estimator is
made. A simulation study is conducted to compare the finite sample behaviors of these estimators based on bias and standard
error. 相似文献