右删失长度偏差数据分位数差的非参数估计

利用长度偏差数据所特有的辅助信息,对带右删失的长度偏差数据的分位数差提出了一种新的非参数估计.该方法提高了估计的有效性,所得的估计量形式简洁,便于计算.同时,本文用经验过程理论建立了该分位数差估计的相合性及渐近正态性,并给出方差估计的重抽样方法.本文还通过数值模拟考察了该估计量在有限样本下的表现,并将其应用到一个关于老年痴呆的实际数据中.     

Semiparametric quantile-difference estimation for length-biased and right-censored data

Science China Mathematics - Prevalent cohort studies frequently involve length-biased and right-censored data, a fact that has drawn considerable attention in survival analysis. In this article, we...     

A class of rank-based test for left-truncated and right-censored data

A class of rank-based tests is proposed for the two-sample problem with left-truncated and right-censored data. The class contains as special cases the extension of log-rank test and Gehan test. The asymptotic distribution theory of the test is presented. The small-sample performance of the test is investigated under a variety of situations by means of Mone Carlo simulations.     

随机缺失数据下样本分位数估计

分位数的估计在生物医学、社会经济调查等领域有着广泛的应用,然而在实际问题的研究中,往往由于各种人为或不可控因素造成数据收集不完全.本文在随机缺失(MAR)假设条件下,利用非参数核补法和局部多重插补法给出了响应变量缺失时样本分位数的估计,并利用经验过程等理论证明了由这两种方法得到的分位数估计的大样本性质,同时,使用重抽样方法给出了估计的渐近方差的估计,模拟结果验证了这两种方法的有效性.文章所提两种方法的优点在于:首先,所提出的缺失修正方法不需要对缺失概率的模型做任何假设;其次,方法亦适用于其他有关参数不可微的估计目标函数;最后,方法很容易地推广到一般M估计的情况,并可以对多个分位数同时进行估计.     

空间半参数变系数部分线性回归中的分位数估计

本文研究了空间数据变系数部分线性回归中的分位数估计. 模型中的参数估计量通过未知系数函数的分段多项式逼近得到, 而未知系数函数的估计量通过将参数估计量代入模型中并通过局部线性逼近得到. 文中推导了未知参数向量估计量的渐近分布, 并建立了未知系数函数估计量在内点及边界点的渐近分布. 通过Monte Carlo 模拟研究了估计量的有限样本性质.     

Confidence bands in nonparametric regression with length biased data

In this paper we deduce a confidence bands construction for the nonparametric estimation of a regression curve from length biased data, where a result from Bickel and Rosenblatt (1973,The Annals of Statistics,1, 1071–1095) is adapted to this new situation. The construction also involves the estimation of the variance of the local linear estimator of the regression, where we use a finite sample modification in order to improve the performance of these confidence bands in the case of finite samples.     

Quantile residual lifetime for left-truncated and right-censored data

This article proposes a simple nonparametric estimator of quantile residual lifetime function under left-truncated and right-censored data. The asymptotic consistency and normality of this estimator are proved and the variance expression is calculated. Two bootstrap procedures are employed in the simulation study, where the latter bootstrap from Zeng and Lin (2008) is 4000 times faster than the former naive one, and the numerical results in both methods show that our estimating approach works well. A real data example is used to illustrate its application.     

Nonparametric estimation under length-biased sampling and Type I censoring: A moment based approach

Observation of lifetimes by means of cross-sectional surveys typically results in left-truncated, right-censored data. In some applications, it may be assumed that the truncation variable is uniformly distributed on some time interval, leading to the so-called length-biased sampling. This information is relevant, since it allows for more efficient estimation of survival and related parameters. In this work we introduce and analyze new empirical methods in the referred scenario, when the sampled lifetimes are at risk of Type I censoring from the right. We illustrate the method with real economic data. Work supported by the Grants PGIDIT02PXIA30003PR and BFM2002-03213.     

Quantile estimation under successive sampling

This paper deals with the estimation, under sampling in two successive occasions, of a finite population quantile. For this sampling design a class of estimators is proposed whose the ratio and difference estimators are particular cases. Asymptotic variance formulae are derived for the proposed estimators, and the optimal matching fraction is discussed. Comparisons are made with existing estimators in a simulation study using a natural population.     

大规模数据的L1惩罚分位数回归方法研究--基于特征筛选和随机抽样方法

为解决大规模数据在进行回归分析时存在的计算内存不足和运行时间较长的问题,提出两个新的回归分析方法:先筛选后抽样的大规模数据L₁惩罚分位数回归方法(FSSLQR)和先抽样后筛选的大规模数据L₁惩罚分位数回归方法(SFSLQR),其数值模拟和实际应用结果表明:FSSLQR和SFSLQR方法不仅能够显著降低计算内存和运行时间,而且其估计预测和变量选择的结果与全量L₁惩罚分位数回归基本一致。此外,与Xu等(2018)提出的大规模数据的L1惩罚分位数回归方法(SLQR)相比,FSSLQR和SFSLQR方法在估计预测、变量选择和运行时间等方面都更具优势。     

Analyzing left-truncated and right-censored data under Cox models with long-term survivors

We analyze left-truncated and right-censored data using Cox proportional hazard models with long-term survivors. The estimators of covariate coefficients and the long-term survivor proportion are obtained by the partial likelihood method, and their asymptotic properties are also established. Simulation studies demonstrate the performance of the proposed estimators, and an application to a real dataset is provided.     

响应变量删失时函数型部分线性分位数回归模型的估计

最近几年,函数型数据分析的理论和应用飞速发展.在许多实际应用里,响应变量往往存在随机右删失的情况.考虑利用函数型部分线性分位数回归模型来刻画函数型和标量预测量与右删失响应变量之间的关系.基于函数型主成分基函数来逼近未知的斜率函数,通过极小化逆概率加权分位数损失函数得到未知系数的估计量.文章的估计方法容易通过加权分位数回...     

左截断数据下非参数回归模型的复合分位数回归估计

利用局部多项式方法研究了误差具有异方差结构的非参数回归模型,在左截断数据下构造了回归函数的复合分位数回归估计,并得到了该估计的渐近正态性结果,最后通过模拟,在服从一些非正态分布的误差下,得到该估计比局部线性估计更有效.     

Quantile regression for longitudinal data

The penalized least squares interpretation of the classical random effects estimator suggests a possible way forward for quantile regression models with a large number of “fixed effects”. The introduction of a large number of individual fixed effects can significantly inflate the variability of estimates of other covariate effects. Regularization, or shrinkage of these individual effects toward a common value can help to modify this inflation effect. A general approach to estimating quantile regression models for longitudinal data is proposed employing ?₁ regularization methods. Sparse linear algebra and interior point methods for solving large linear programs are essential computational tools.     

面板数据分位数回归模型求解的模式搜索法

本文应用最优化理论,对固定效应的面板数据分位数回归模型,提出一种模式搜索方法,此方法可以同时估计出所有分位点处的解释变量系数和所有个体的固定效应值。进一步利用蒙特卡洛模拟比较现有文献中涉及的面板数据分位数回归方法,结果显示无论误差项是否满足经典假设,模式搜索分位数回归法较之其他分位数回归估计方法更为有效.     

Regression Adjustment for Noncrossing Bayesian Quantile Regression

A two-stage approach is proposed to overcome the problem in quantile regression, where separately fitted curves for several quantiles may cross. The standard Bayesian quantile regression model is applied in the first stage, followed by a Gaussian process regression adjustment, which monotonizes the quantile function while borrowing strength from nearby quantiles. The two-stage approach is computationally efficient, and more general than existing techniques. The method is shown to be competitive with alternative approaches via its performance in simulated examples. Supplementary materials for the article are available online.     

Inference for the treatment effects in two sample problems with right-censored and length-biased data

In the study of comparing treatment effects, the data structures of two samples may be different. In this paper, we develop a unified semiparametric estimating equation approach to estimate various types of treatment effects with right-censored and length-biased data based on a semiparametric two-sample model. The large sample properties of the proposed estimators are derived and numerical studies are conducted to illustrate the proposed methods.     

失混合效应模型的分位回归及变量选择

纵向数据常常用正态混合效应模型进行分析.然而,违背正态性的假定往往会导致无效的推断.与传统的均值回归相比较,分位回归可以给出响应变量条件分布的完整刻画,对于非正态误差分布也可以给稳健的估计结果．本文主要考虑右删失响应下纵向混合效应模型的分位回归估计和变量选择问题．首先,逆删失概率加权方法被用来得到模型的参数估计．其次,结合逆删失概率加权和LASSO惩罚变量选择方法考虑了模型的变量选择问题.蒙特卡洛模拟显示所提方法要比直接删除删失数据的估计方法更具优势．最后,分析了一组艾滋病数据集来展示所提方法的实际应用效果．     

��λ���ع�Ĺ⻬������Ȼ

For linear quantile regression model, this paper proves that the test statistics, besed on smoothed empirical likelihood (SEL) method and least absolute deviation (LAD) method, both converge weakly to a noncentral Chi-square distribution under the local alternatives $H_1:beta=beta_0+a_n$, where $beta$ is the true parameter. Simulation results show that the SEL method is more efficient than the LAD method.