随机右删失数据下半参数线性变换模型的经验似然推断

本文研究了响应变量随机右删失情形下半参数线性变换模型的经验似然推断问题.构造了参数的经验似然比检验统计量,证明了经验似然比检验统计量的渐近分布为加权卡方分布.在此基础上,对经验似然比检验统计量进行了调整,证明了调整的经验似然比检验统计量的渐近分布为标准的卡方分布.基于经验似然和调整的经验似然方法,分别给出了回归参数的一定置信水平的置信域.最后对本文的方法和传统的正态逼近方法进行了模拟比较,模拟结果显示,从置信域的大小和经验覆盖概率两个角度看,本文的方法均比正态逼近方法优越.     

随机右删失数据下半参数线性变换模型的经验似然推断北大核心CSCD

本文研究了响应变量随机右删失情形下半参数线性变换模型的经验似然推断问题.构造了参数的经验似然比检验统计量,证明了经验似然比检验统计量的渐近分布为加权卡方分布.在此基础上,对经验似然比检验统计量进行了调整,证明了调整的经验似然比检验统计量的渐近分布为标准的卡方分布.基于经验似然和调整的经验似然方法,分别给出了回归参数的一定置信水平的置信域.最后对本文的方法和传统的正态逼近方法进行了模拟比较,模拟结果显示,从置信域的大小和经验覆盖概率两个角度看,本文的方法均比正态逼近方法优越.     

基于经验似然的Logistic回归模型的变点检验

基于经验似然对Logistic回归模型进行变点检验及估计.通过建立变点模型,构造经验对数似然比统计量,在大样本下,证明了经验对数似然比统计量与经典参数对数似然比统计量具有相同的极值分布,同时得到变点的估计及估计的相合性,并通过数值模拟及实例说明经验似然方法检验变点的可行性.     

基于离散观测的OU型过程的经验似然估计

基于离散观测样本,借助条件特征函数,提出了OU型过程参数的经验似然估计,并证明了最大经验似然估计的相合性和渐近正态性,同时证明了在适当的附加条件下,该估计是渐近有效的.当驱动Lévy过程具有某种特殊形式时,发现OU型过程的强度参数能够首先估计出来.在此特殊情形下,提出了OU型过程中其余参数的最大经验似然估计,并讨论了其相合性、渐近正态性和渐近有效性.基于经验似然比统计量,给出了参数检验和估计方程检验的似然比检验方法.模拟显示所提出的估计方法是准确和稳定的.     

缺失数据均值推断的经验似然方法

研究了缺失数据的均值推断问题.在随机缺失及半参数模型的假设下,设计了基于影响函数理论的经验似然推断方法,证明了所构造的对数经验似然比检验统计量具有非参数Wilks性质.此外,该经验似然方法可以利用辅助协变量中提供的附加信息来提高检验的功效.在近邻备择假设下,计算了检验统计量的功效,并且通过一些模拟考察了该方法在有限样本下的表现.     

缺失数据均值推断的经验似然方法

研究了缺失数据的均值推断问题.在随机缺失及半参数模型的假设下,设计了基于影响函数理论的经验似然推断方法,证明了所构造的对数经验似然比检验统计量具有非参数Wilks性质.此外,该经验似然方法可以利用辅助协变量中提供的附加信息来提高检验的功效.在近邻备择假设下,计算了检验统计量的功效,并且通过一些模拟考察了该方法在有限样本下的表现.     

变系数部分线性模型的拟合优度检验

本文考虑变系数部分线性模型的拟合优度检验问题.基于Profile经验似然方法,构造了参数部分和非参数部分的经验似然比检验统计量.并证明了其满足Wilks'现象,进而得到了一定置信水平的拒绝域.最后通过数据模拟,讨论了其检验功效.     

半函数线性模型的k近邻经验似然推断

将k近邻方法应用到经验似然方法中,并以此来研究函数型数据下,半函数部分线性模型的估计问题.通过构造参数分量的对数经验似然比函数,得到该经验对数似然比依分布收敛于χ2分布,同时给出了非参数部分的估计值和收敛速度,并给出了经验似然方法在模拟研究中的应用.     

相依序列密度函数的经验似然推断

本文利用了强平稳$m-$相依序列的特殊性质,讨论了$m-$相依序列密度函数的经验似然推断, 给出了似然比统计量的极限分布,可构造参数的经验似然置信区间. 并且通过模拟计算来说明有限样本下应用经验似然方法的合理性.     

重尾序列均值变点的经验似然比检验

本文通过经验似然思想建立假设检验的方法,研究了重尾序列均值变点的检测问题.首先,基于重尾模型,在原假设和备择假设下得到经验似然函数.其次,基于经验似然函数构造似然比检验统计量,并给出在原假设成立时该似然比统计量的渐近分布.最后,进行Monte Carlo数值模拟验证该方法的有效性,模拟结果表明本方法对重尾序列均值变点的检测具有良好效果.     

含有截断和缺失数据的经验似然推断

本文将经验似然的方法应用到同时包含截断和缺失数据的情况. 通过定义调整后的经验似然比, 证明它服从$\chi^2$分布. 利用随机模拟, 比较经验似然和正态方法的优劣. 结果发现经验似然方法在很多情况下都优于正态方法.     

在分层抽样下有效利用辅助信息及含于层总体大小中的信息的经验似然方法

本文考虑用在分层随机抽样下的经验似然方法来获得有限总体参数的估计量\bd 我们指出, 经验似然方法非常自然地结合辅助信息和含于层总体大小中的信息\bd 我们的结果显示, 由经验似然方法可获得有效估计.     

Empirical likelihood for heteroscedastic partially linear models

We make empirical-likelihood-based inference for the parameters in heteroscedastic partially linear models. Unlike the existing empirical likelihood procedures for heteroscedastic partially linear models, the proposed empirical likelihood is constructed using components of a semiparametric efficient score. We show that it retains the double robustness feature of the semiparametric efficient estimator for the parameters and shares the desirable properties of the empirical likelihood for linear models. Compared with the normal approximation method and the existing empirical likelihood methods, the empirical likelihood method based on the semiparametric efficient score is more attractive not only theoretically but empirically. Simulation studies demonstrate that the proposed empirical likelihood provides smaller confidence regions than that based on semiparametric inefficient estimating equations subject to the same coverage probabilities. Hence, the proposed empirical likelihood is preferred to the normal approximation method as well as the empirical likelihood method based on semiparametric inefficient estimating equations, and it should be useful in practice.     

Empirical Likelihood for a Class of Functionals of Survival Distribution with Censored Data

The empirical likelihood was introduced by Owen, although its idea originated from survival analysis in the context of estimating the survival probabilities given by Thomas and Grunkemeier. In this paper, we investigate how to apply the empirical likelihood method to a class of functionals of survival function in the presence of censoring. We define an adjusted empirical likelihood and show that it follows a chi-square distribution. Some simulation studies are presented to compare the empirical likelihood method with the Studentized-t method. These results indicate that the empirical likelihood method works better than or equally to the Studentized-t method, depending on the situations.     

平衡增加的经验欧氏似然

经验(欧氏)似然方法是近年来非常流行的一种非参数统计方法.针对经验(欧氏)似然的凸包限制和计算复杂问题,本文借助Emerson和Owen (2009)所提出的平衡增加思想对经验欧氏似然进行修正,得到了平衡增加的经验欧氏似然.随后论文从理论和模拟两个方面进行了研究.理论上给出了该方法与经验欧氏似然检验函数之间的联系,即在固定的样本量n下随着添加点位置的连续变化,检验方法可以从简单的均值增加经验欧氏似然变化到经验欧氏似然检验;模拟结果显示,适当选取调整因子,平衡增加的经验欧氏似然相对于(调整)经验欧氏似然而言,在大多数情况下,其分布更接近于对应的极限分布.     

Empirical likelihood hypothesis test on mean with inequality constraints

Hypothesis test on the population mean with various inequality constraints is studied in this paper.The empirical likelihood method is applied to construct test statistics.Limiting distributions of the empirical likelihood ratio test statistics are proven to be a weighted mixture of chi-square distributions.Numerical results are presented to show the validity of the proposed method.     

Penalized Empirical Likelihood Estimation for Partially Linear Single Index Panel Model with Fixed Effects

This paper constructs a penalized empirical likelihood estimation method via quadratic inference function method, filter method and empirical likelihood estimation method. Under some regular conditions, we derived the large sample properties of estimators and show that the proposed empirical likelihood ratio is asymptotically to chi-square distribution. Furthermore, the infinite sample performance of the proposed method is evaluated by Monte Carlo simulation and real data analysis.     

�̶�ЧӦ�������Ե�ָ�����ģ�͵ijͷ�������Ȼ����

??This paper constructs a penalized empirical likelihood estimation method via quadratic inference function method, filter method and empirical likelihood estimation method. Under some regular conditions, we derived the large sample properties of estimators and show that the proposed empirical likelihood ratio is asymptotically to chi-square distribution. Furthermore, the infinite sample performance of the proposed method is evaluated by Monte Carlo simulation and real data analysis.     

A modification of profile empirical likelihood for the exponential-tilt model

We consider semiparametric models whose infinite-dimensional parameter corresponds to a probability distribution. The NPMLE based on the profile empirical likelihood for this kind of semiparametric model has attracted considerable interest. We propose the use of a modified profile empirical likelihood to improve the accuracy of this estimation. We consider applications to the exponential-tilt model and show that the accuracy of the proposed estimator is better than that of the conventional NPMLE by numerical study.