具有随机右删失随机变量分位数的经验似然推断（英文）

本文研究了具有随机右删失随机变量分位数的置信域的构造.利用经验似然和截尾值估算相结合的方法,给出了分位数的对数经验似然比统计量,在较少的条件下证明了该统计量的极限分布为自由度为1的x~2分布.使得完全数据下的分位数的经验似然推断方法应用到非完全数据中.     

分数填补下两总体分位数差异的半经验似然推断

在完全随机缺失机制情形,利用分数填补法填补缺失值,然后用经验似然方法构造两总体分位数差异的半经验似然比统计量,证明其渐近服从加权X~2分布并构造了相应的半经验似然置信区间.     

回归模型的同方差检验

本文利用局部经验似然和WNW方法对条件分布函数和条件分位数进行估计,并利用条件分位数的方法对回归模型中的误差方差进行了同方差假设检验,获得了零假设下检验统计量的渐近分布为X2分布．模拟计算表明同方差假设检验的条件分位数方法具有较好的功效．     

右删失数据下分位数回归的光滑经验似然检验

关于线性分位数回归模型的参数检验问题,对完全观测数据,已有文献用经验似然(EL)法和光滑经验似然(SEL)法构造的检验统计量在原假设下均以卡方分布χ_M~2为渐近分布.对右删失数据,已有文献用EL法构造的检验统计量以加权卡方分布为渐近分布,而权重是待估的.对右删失数据,本文用EL法和SEL法构造的检验统计量在原假设下均依分布收敛到χ_M~2,因此无需估计权重.由于SEL法的估计函数是光滑的,故可以进行Bartlett纠偏.随机模拟结果表明与已有的方法相比,SEL法经过Bartlett纠偏后有更高的精度.     

附加信息下的p分位数光滑经验似然置信区间

Chen和Hall在1993年使用光滑的经验似然方法建立了p分位数置信区间.本文在有部分附加信息的情况下使用了光滑的经验似然方法建立了p分位数的置信区间,从渐近功效函数方面对置信区间做了比较,后者优于前者.并且置信概率误差的阶为n-1,证明了本文所建立的置信区间是可以Bartlett修正的.     

分数填补下两总体分位数差异的经验似然置信区间

设有两个非参数总体,其样本数据不完全,用分数填补法补足缺失数据,得到两总体的"完全"样本数据,在此基础上构造两总体分位数差异的经验似然置信区间.模拟结果显示,分数填补法可以得到更加精确的置信区间.     

经验似然统计推断方法发展综述

本文在介绍经验似然方法的基础上，进一步介绍这一方法在统计推断中的应用，具体地介绍了这一方法在总体均值推断、线性模型推断、分位数推断、估计方程推断及利用辅助信息进行推断等几种重要统计推断中的应用，同时也介绍了这一方法最近在不完全数据中的应用及由此所提出的被估计、被调整及bootstrap经验似然方法。     

分位数置信区间的估计方法分析

构造了基于分位数两种估计量的渐近置信区间,并找到分位数基于样本次序统计量的渐近置信区间.同时,建立了基于分布函数核估计定义的分位数估计量的渐近正态性,并使用经验似然方法构造出分位数的两种渐近置信区间.在模拟分析中,基于置信区间的平均长度和覆盖率,分析构造分位数的五种渐近置信区间的有限样本表现.     

随机插补下两线性模型中响应变量分位数差异的经验似然置信区间

设两个样本数据不完全的线性模型,其中协变量的观测值不缺失,响应变量的观测值随机缺失。采用随机回归插补法对响应变量的缺失值进行补足,得到两个线性回归模型的"完全"样本数据,在一定条件下得到两响应变量分位数差异的对数经验似然比统计量的极限分布为加权x_1~2,并利用此结果构造分位数差异的经验似然置信区间。模拟结果表明在随机插补下得到的置信区间具有较高的覆盖精度。     

����ʼ�Ȩ���������ģ������Ӧ������λ������ľ�����Ȼͳ���ƶ�

本文对两个样本数据不完全的线性模型展开讨论, 其中线性模型协变量的观测值不缺失, 响应变量的观测值随机缺失(MAR). 我们采用逆概率加权填补方法对响应变量的缺失值进行补足, 得到两个线性回归模型``完全'样本数据, 在``完全'样本数据的基础上构造了响应变量分位数差异的对数经验似然比统计量. 与以往研究结果不同的是本文在一定条件下证明了该统计量的极限分布为标准, 降低了由于权系数估计带来的误差, 进一步构造出了精度更高的分位数差异的经验似然置信区间.     

��ɾʧ�����·�λ���ع�Ĺ⻬������Ȼ����

This paper is focused on testing the parameters of the quantile regression models. For complete observation, it is shown in literature that the test statistics, based on empirical likelihood (EL) method and smoothed empirical likelihood (SEL) method, both converge weakly to the standard Chi-square distribution $\chi_M^2$ under the null hypothesis. For right censored data, the statistics in literature, by the EL method, have a weighted Chi-square limiting distribution, but the weights are unknown. In this paper, we show that the statistics based on the EL method and the SEL method also converge weakly to $\chi_M^2$ under the null hypothesis, so there is no need to estimate any weights. As its estimating function is smoothed, the SEL method can be Bartlett corrected. Numerical results show that the SEL method, via Bartlett correction, outperforms some recent methods.     

右删失数据下非线性回归模型的经验似然推断

考虑随机右删失数据下非线性回归模型,提出了模型中未知参数的调整的经验对数似然比统计量.在一定的条件下,证明了.所提出的的统计量具有渐近χ~2分布,由此结果构造了兴趣参数的置信域.通过模拟研究,对经典的经验似然、调整的经验似然和非线性最小二乘方法在有限样本下进行了比较,并对氯离子浓度试验数据进行了分析.     

截断情况下线性回归模型响应变量均值的经验似然

本文讨论了在带有截断情况的线性回归模型中 ,响应变量均值的估计问题 .将经验似然的方法应用到带有截断情况的回归模型中 ,在估计响应变量的均值时构造了调整的经验似然统计量 ,证明了在一定的条件下 ,该统计量渐近服从 χ2 分布 ,给出了均值的置信区间 ,并与正态下得到的结果进行了比较 ,模拟的结果说明了经验似然的优良性 .     

Weighted Empirical Likelihood Ratio Confidence Intervals for the Mean with Censored Data

We propose a procedure to construct the empirical likelihood ratio confidence interval for the mean using a resampling method. This approach leads to the definition of a likelihood function for censored data, called weighted empirical likelihood function. With the second order expansion of the log likelihood ratio, a weighted empirical likelihood ratio confidence interval for the mean is proposed and shown by simulation studies to have comparable coverage accuracy to alternative methods, including the nonparametric bootstrap-t. The procedures proposed here apply in a unified way to different types of censored data, such as right censored data, doubly censored data and interval censored data, and computationally more efficient than the bootstrap-t method. An example of a set of doubly censored breast cancer data is presented with the application of our methods.     

Confidence Intervals and Accuracy Estimation for Heavy-Tailed Generalized Pareto Distributions

The generalized Pareto distribution (GPD) is a two-parameter family of distributions which can be used to model exceedances over a threshold. We compare the empirical coverage of some standard bootstrap and likelihood-based confidence intervals for the parameters and upper p-quantiles of the GPD. Simulation results indicate that none of the bootstrap methods give satisfactory intervals for small sample sizes. By applying a general method of D. N. Lawley, correction factors for likelihood ratio statistics of parameters and quantiles of the GPD have been calculated. Simulations show that for small sample sizes accuracy of confidence intervals can be improved by incorporating the computed correction factors to the likelihood-based confidence intervals. While the modified likelihood method has better empirical coverage probability, the mean length of produced intervals are not longer than corresponding bootstrap confidence intervals. This article also investigates the performance of some bootstrap methods for estimation of accuracy measures of maximum likelihood estimators of parameters and quantiles of the GPD.     

Efficient construction of a smooth nonparametric family of empirical distributions and calculation of bootstrap likelihood

This paper considers the efficient construction of a nonparametric family of distributions indexed by a specified parameter of interest and its application to calculating a bootstrap likelihood for the parameter. An approximate expression is obtained for the variance of log bootstrap likelihood for statistics which are defined by an estimating equation resulting from the method of selecting the first-level bootstrap populations and parameters. The expression is shown to agree well with simulations for artificial data sets based on quantiles of the standard normal distribution, and these results give guidelines for the amount of aggregation of bootstrap samples with similar parameter values required to achieve a given reduction in variance. An application to earthquake data illustrates how the variance expression can be used to construct an efficient Monte Carlo algorithm for defining a smooth nonparametric family of empirical distributions to calculate a bootstrap likelihood by greatly reducing the inherent variability due to first-level resampling.     

Empirical likelihood method for intermediate quantiles

Intermediate quantiles play an important role in the statistics of extremes with particular applications in risk management. For interval estimation of quantiles, Chen and Hall (1993) proposed the so-called smoothed empirical likelihood method. In this paper, we apply the method in Chen and Hall (1993) to construct confidence intervals for an intermediate quantile by deriving the corresponding Wilks Theorem.     

New estimating equation approaches with application in lifetime data analysis

Estimating equation approaches have been widely used in statistics inference. Important examples of estimating equations are the likelihood equations. Since its introduction by Sir R. A. Fisher almost a century ago, maximum likelihood estimation (MLE) is still the most popular estimation method used for fitting probability distribution to data, including fitting lifetime distributions with censored data. However, MLE may produce substantial bias and even fail to obtain valid confidence intervals when data size is not large enough or there is censoring data. In this paper, based on nonlinear combinations of order statistics, we propose new estimation equation approaches for a class of probability distributions, which are particularly effective for skewed distributions with small sample sizes and censored data. The proposed approaches may possess a number of attractive properties such as consistency, sufficiency and uniqueness. Asymptotic normality of these new estimators is derived. The construction of new estimation equations and their numerical performance under different censored schemes are detailed via Weibull distribution and generalized exponential distribution.     

Empirical Likelihood Semiparametric Regression Analysis under Random Censorship

This paper considers large sample inference for the regression parameter in a partly linear model for right censored data. We introduce an estimated empirical likelihood for the regression parameter and show that its limiting distribution is a mixture of central chi-squared distributions. A Monte Carlo method is proposed to approximate the limiting distribution. This enables one to make empirical likelihood-based inference for the regression parameter. We also develop an adjusted empirical likelihood method which only appeals to standard chi-square tables. Finite sample performance of the proposed methods is illustrated in a simulation study.     

Empirical Likelihood Ratio With Arbitrarily Censored/Truncated Data by EM Algorithm

The empirical likelihood is a general nonparametric inference procedure with many desirable properties. Recently, theoretical results for empirical likelihood with certain censored/truncated data have been developed. However, the computation of empirical likelihood ratios with censored/truncated data is often nontrivial. This article proposes a modified self-consistent/EM algorithm to compute a class of empirical likelihood ratios for arbitrarily censored/truncated data with a mean type constraint. Simulations show that the chi-square approximations of the log-empirical likelihood ratio perform well. Examples and simulations are given in the following cases: (1) right-censored data with a mean parameter; and (2) left-truncated and right-censored data with a mean type parameter.