检索结果-南通市图书馆

Gini Correlation for Feature Screening

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2021年第3期37卷 590-601页

作者： Jun-ying zhang Xiao-feng LIU ri-{2. zhang Hang-WANG department of Mathematics Taiyuan University of TechnologyTaiyuan 030024China College of Data Science Taiyuan University of TechnologyTaiyuan 030024China School of Finance and statistics East China Normal UniversityShanghai 200241China department of Mathematics Shanxi Datong UniversityDatong 037009China

In this paper we propose the Gini correlation screening(GCS)method to select the important variables with ultrahigh dimensional *** new procedure is based on the Gini correlation coefficient via the covariance between the response and the rank of the predictor variables rather than the Pearson correlation and the Kendallτcorrelation *** new method does not require imposing a specific model structure on regression functions and only needs the condition which the predictors and response have continuous distribution *** demonstrate that,with the number of predictors growing at an exponential rate of the sample size,the proposed procedure possesses consistency in ranking,which is both useful in its own right and can lead to consistency in *** procedure is computationally efficient and simple,and exhibits a competent empirical performance in our intensive simulations and real data analysis.

关键词： ultrahigh dimension Gini correlation coefficient variable screening feature ranking

Nonparametric Regression with Interval-Censored Data

在线全文

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2014年第8期30卷 1422-1434页

作者： Wen Li DENG Zu Kang ZHENG ri quan {2. School of Mathematics and Information Science Jiangxi Normal University department of statistics School of ManagementFudan University department of statistics School of Finance and StatisticsEast China Normal University

In many medical studies,the prevalence of interval censored data is increasing due to periodic monitoring of the progression status of a *** nonparametric regression model,when the response variable is subjected to interval-censoring,the regression function could not be estimated by traditional methods *** the censored data,we construct a new response variable which has the same conditional expectation as the original *** on the new variable,we get a nearest neighbor estimator of the regression *** is established that the estimator has strong consistency and asymptotic *** relevant simulation reports are given.

关键词： Interval-censored data regression function nearest neighbor estimator

Estimation of Semi-Varying Coefficient Model with Surrogate Data and Validation Sampling

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2013年第3期29卷 645-660页

作者： Ya-zhao L ri-quan {2. Zhen-sheng HUANG department of statistics East China Normal University Institute of Operational Research and Cybernetics Hangzhou Dianzi University department of Mathematics Shanxi Datong University School of Science Nanjing University of Science and Technology

In this paper, we investigate the estimation of semi-varying coefficient models when the nonlinear covariates are prone to measurement error. With the help of validation sampling, we propose two estimators of the parameter and the coefficient functions by combining dimension reduction and the profile likelihood methods without any error structure equation specification or error distribution assumption. We establish the asymptotic {2.ity of proposed estimators for both the parametric and nonparametric parts and show that the proposed estimators achieves the best convergence rate. Data-driven bandwidth selection methods are also discussed. Simulations are conducted to evaluate the finite sample property of the estimation methods proposed.

关键词： asymptotic normality profile likelihood measurement error validation sampling semi-varying coefficient model

The Proportional Hazards Model for Multiple Type Recurrent Gap Times

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2016年第1期32卷 221-230页

作者： Ji-cai LIU Huan-bin LIU ri-quan {2. department of statistics East China Normal UniversityShanghai 200241China College of Mathematics and Computer Science Huanggang normal university Huangzhou 438000China department of Mathematics Shanxi Datong UniversityDatong 037009China

Recurrent events data and gap times between recurrent events are frequently encountered in many clinical and observational studies,and often more than one type of recurrent events is of *** this paper,we consider a proportional hazards model for multiple type recurrent gap times data to assess the effect of covaxiates on the censored event processes of *** estimating equation approach is used to obtain the estimators of regression coefficients and baseline cumulative hazard *** examine asymptotic properties of the proposed *** sample properties of these estimators are demonstrated by simulations.

关键词： proportional hazards model estimating equation multiple type recurrent events gap times semiparametric inference

Inference on Varying-Coefficient Partially Linear Regression Model

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2015年第1期31卷 139-156页

作者： Jing-yan FENG ri-quan {2. Yi-qiang LU department of Mathematics Shanxi Datong University department of statistics East China Normal University Institute of Electronic Technology the PLA Information Engineering University

The varying-coefficient partially linear regression model is proposed by combining nonparametric and varying-coefficient regression procedures. Wong, et al. （2.08） proposed the model and gave its estimation by the local linear method. In this paper its inference is addressed. Based on these estimates, the generalized like- lihood ratio test is established. Under the null hypotheses the normalized test statistic follows a x2.distribution asymptotically, with the scale constant and the degrees of freedom being independent of the nuisance param- eters. This is the Wilks phenomenon. Furthermore its asymptotic power is also derived, which achieves the optimal rate of convergence for nonparametric hypotheses testing. A simulation and a real example are used to evaluate the performances of the testing procedures empirically.

关键词： asymptotic normality varying-coefficient partially linear regression model generalized likelihoodratio test Wilks phenomenon xi-distribution.

Bayesian Regularized Regression Based on Composite quantile Method

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2016年第2期32卷 495-512页

作者： Wei-hua ZHAO ri-quan {2. Ya-zhao LU Ji-cai LIU School of statistics East China Normal UniversityShanghai 200241China School of Science NanTong UniversityNanTong 226007China department of Mathematics Shanxi Datong UniversityDatong 037009China

Recently, variable selection based on penalized regression methods has received a great deal of attention, mostly through frequentist＇s models. This paper investigates regularization regression from Bayesian perspective. Our new method extends the Bayesian Lasso regression （Park and Casella, 2.08） through replacing the l{2. square loss and Lasso penalty by composite quantile loss function and adaptive Lasso penalty, which allows different penalization parameters for different regression coefficients. Based on the Bayesian hierarchical model framework, an efficient Gibbs sampler is derived to simulate the parameters from posterior distributions. Furthermore, we study the Bayesian composite quantile regression with adaptive group Lasso penalty. The distinguishing characteristic of the newly proposed method is completely data adaptive without requiring prior knowledge of the error distribution. Extensive simulations and two real data examples are used to examine the good performance of the proposed method. All results confirm that our novel method has both robustness and high efficiency and often outperforms other approaches.

关键词： composite quantile regression variable selection Lasso adaptive Lasso, Gibbs sampler

在线全文

学校读者我要写书评

暂无评论

相依数据非参数核估计的收敛速度

苏州科技学院学报（自然科学版） 2003年第1期20卷 8-12,25页

作者：张日权华东师范大学统计系上海200062

在非参数和半参数模型中,不论数据是独立的还是相依的,都涉及到对未知均值函数或者对某函数的未知条件期望的估计。文章针对这一问题,在数据为混合相依的条件下,给出一般函数条件数学期望的估计,并讨论了它的收敛速度。

关键词：非参数模型半参数模型 β-核估计混合相依收敛速度数学期望统计分析

在线全文

学校读者我要写书评

暂无评论

比例数据的贝叶斯变量选择

数理统计与管理 2018年第3期37卷 459-468页

作者：赵为华张日权南通大学理学院江苏南通226019 华东师范大学统计学院上海200241

本文在Bernoulli拟似然框架下基于贝叶斯方法研究比例数据的变量选择问题。通过引入系数的“spike and slab”先验分布，应用EM算法提出了基于门限规则的变量选择方法。该方法具有计算量小、模型正确识别率高等特点。数值模拟研究和实... 详细信息

本文在Bernoulli拟似然框架下基于贝叶斯方法研究比例数据的变量选择问题。通过引入系数的“spike and slab”先验分布，应用EM算法提出了基于门限规则的变量选择方法。该方法具有计算量小、模型正确识别率高等特点。数值模拟研究和实例分析验证了所提方法的有效性。

关键词：比例数据贝叶斯变量选择 EM算法

DNA methylation markers in the diagnosis and prognosis of common leukemias

在线全文

学校读者我要写书评

暂无评论

Signal Transduction and Targeted Therapy 2020年第1期5卷 2468-2477页

作者： Hua Jiang Zhiying Ou Yingyi He Meixing Yu Shaoqing Wu Gen Li Jie Zhu Ru zhang Jiayi Wang Lianghong Zheng Xiaohong zhang Wenge Hao Liya He Xiaoqiong Gu Qingli {2. Edward zhang Huiyan Luo Wei Wei Zhihuan Li Guangxi Zang Charlotte zhang Tina Poon Daniel zhang Ian Ziyar Run-ze zhang Oulan Li Linhai Cheng Taylor Shimizu Xinping Cui Jian-kang Zhu Xin Sun Kang zhang Guangzhou Women and Children’s Medical Center Guangzhou Medical UniversityGuangzhou 510623China Guangzhou Regenerative Medicine and Health Guangdong Laboratory Guangzhou 510005China State Key Laboratory of Oncology Sun Yat-sen University Cancer CenterGuangzhou 510060China department of statistics and Institute for Integrative Genome Biology University of California RiversideRiversideCA 92521USA shanghai Center for Plant Stress Biology Shanghai Institute for Biological SciencesChinese Academy of SciencesShanghai 210602China Faculty of Medicine Macao University of Science and TechnologyTaipaMacaoChina

The ability to identify a specific type of leukemia using minimally invasive biopsies holds great promise to improve the diagnosis,treatment selection,and prognosis prediction of *** genome-wide methylation profiling and machine learning methods,we investigated the utility of CpG methylation status to differentiate blood from patients with acute lymphocytic leukemia(ALL)or acute myelogenous leukemia(AML)from normal *** established a CpG methylation panel that can distinguish ALL and AML blood from normal blood as well as ALL blood from AML blood with high sensitivity and *** then developed a methylation-based survival classifier with 2. CpGs for ALL and 2. CpGs for AML that could successfully divide patients into high-{2.sk and low-{2.sk groups,with significant differences in clinical outcome in each leukemia ***,these findings demonstrate that methylation profiles can be highly sensitive and specific in the accurate diagnosis of ALL and AML,with implications for the prediction of prognosis and treatment selection.

关键词： diagnosis prognosis acute