检索结果-内蒙古大学图书馆

The impact of covariate misclassification using generalized linear regression under covariate-adaptive randomization

引用

STATISTICAL METHODS IN MEDICAL RESEARCH 2018年第1期27卷 20-34页

作者： Fan, Liqiong Yeatts, Sharon D. Wolf, Bethany J. McClure, Leslie A. Selim, Magdy Palesch, Yuko Y. Med Univ South Carolina Dept Publ Hlth Sci 135 Cannon StSuite 303MSC 835 Charleston SC 29425 USA Drexel Univ Dept Epidemiol & Biostat Philadelphia PA 19104 USA Beth Israel Deaconess Med Ctr Dept Neurol Div Cerebrovasc Dis Boston MA 02215 USA

Under covariate adaptive randomization, the covariate is tied to both randomization and analysis. Misclassification of such covariate will impact the intended treatment assignment;further, it is unclear what the appropriate analysis strategy should be. We explore the impact of such misclassification on the trial's statistical operating characteristics. Simulation scenarios were created based on the misclassification rate and the covariate effect on the outcome. Models including unadjusted, adjusted for the misclassified, or adjusted for the corrected covariate were compared using logistic regression for a binary outcome and Poisson regression for a count outcome. For the binary outcome using logistic regression, type I error can be maintained in the adjusted model, but the test is conservative using an unadjusted model. Power decreased with both increasing covariate effect on the outcome as well as the misclassification rate. Treatment effect estimates were biased towards the null for both the misclassified and unadjusted models. For the count outcome using a Poisson model, covariate misclassification led to inflated type I error probabilities and reduced power in the misclassified and the unadjusted model. The impact of covariate misclassification under covariate-adaptive randomization differs depending on the underlying distribution of the outcome.

关键词： Covariate-adaptive randomization generalized linear regression covariate misclassification

来源：评论

学校读者我要写书评

暂无评论

Distributed non-convex regularization for generalized linear regression

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartA期252卷

作者： Sun, Xiaofei Zhang, Jingyu Liu, Zhongmo Polat, Kemal Gai, Yujie Gao, Wenliang Shandong Technol & Business Univ Sch Stat Yantai Peoples R China Natl Univ Malaysia Grad Sch Business Bangi Malaysia Bolu Abant Izzet Baysal Univ Dept Elect & Elect Engn Bolu Turkiye Cent Univ Finance & Econ Sch Stat & Math Beijing Peoples R China Mianyang Teachers Coll Sch Econ & Management Mianyang Peoples R China

Distributed penalized generalized linear regression algorithms have been widely studied in recent years. However, they all assume that the data should be randomly distributed. In real applications, this assumption is not necessarily true, since the whole data are often stored in a non-random manner. To tackle this issue, a non- convex penalized distributed pilot sample surrogate negative log-likelihood learning procedure is developed, which can realize distributed high-dimensional variable selection for generalized linear models, and be adaptive to the non-random situations. The established theoretical results and numerical studies all validate the proposed method.

关键词： generalized linear regression Big data Variable selection Regularized learning

来源：评论

学校读者我要写书评

暂无评论

Designing Evaluation Indices for Joint Operation Systems Base on Random Forest with generalized linear regression Algorithm

Designing Evaluation Indices for Joint Operation Systems Bas...

引用

作者： Peng Liu Zeyu Zhou Xinghua Qian Yijiang Xu General Department of information and electronics China Ship Research and Development Academy

Joint operation system is a typical complex system with nonlinear,emergent properties and *** capability index selection methods cannot describe the capability of the joint operation system objectively and accurately because of the subjectivity and randomness in the process of ***,the joint operation simulation experiment based on simulation deduction system is designed,and the assembled machine learning model is built,the Random Forest with generalized linear regression algorithm,to farm the multidimensional and holographic operation data *** random forest algorithm model is used to deeply mine the "multi angle and full dimension" confrontation data obtained from the simulation experiment to screen the significant basic parameter indexes of joint operation strike-capability,and on this basis,the quadratic linear regression is carried ***,the important target threat index of joint operation system,which reflects the complex characteristics of joint operation system,such as operational uncertainty,adaptability and emergence,is *** provides a feasible decisionmaking basis for the commander to adjust the operational plan in real time and evaluate and predict the plan.

关键词： Random Forest generalized linear regression joint operation

来源：评论

学校读者我要写书评

暂无评论

generalized spatial linear regression model for spatial prediction

引用

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence 2005年第6期18卷 708-712页

作者： Wang, Ru-Jing Teng, Ming-Gui Department of Automation University of Science and Technology of China Hefei 230027 China Institute of Intelligent Machines Chinese Academy of Sciences Hefei 230031 China

The universal Kriging model and the generalized linear regression model, which have different emphases, are the most often used methods to predict the attribute value for spatial object. In this paper, a new generalized spatial linear regression model, which integrates two models according to practical problems, is proposed, and the parameters through this mixed model are estimated. The new method holds virtues of the two models, and experiments prove that the generalized spatial linear regression model can predict more accurately.

关键词： generalized linear regression Mixed model Spatial prediction Universal Kriging

来源：评论

学校读者我要写书评

暂无评论

Least angle regression in tangent space and LASSO for generalized linear models

引用

Behaviormetrika 2025年第1期52卷 179-196页

作者： Hirose, Yoshihiro School of Interdisciplinary Mathematical Science Meiji University 4-21-1 Nakano Nakano-ku Tokyo 164-8525 Japan

This study proposes sparse estimation methods for the generalized linear models, which run one of least angle regression (LARS) and least absolute shrinkage and selection operator (LASSO) in the tangent space of the manifold of the statistical model. This study approximates the statistical model and subsequently uses exact calculations. LARS was proposed as an efficient algorithm for parameter estimation and variable selection for the normal linear model. The LARS algorithm is described in terms of Euclidean geometry regarding the correlation as the metric of the parameter space. Since the LARS algorithm only works in Euclidean space, we transform a manifold of the statistical model into the tangent space at the origin. In the generalized linear regression, this transformation allows us to run the original LARS algorithm for the generalized linear models. The proposed methods are efficient and perform well. Real-data analysis indicates that the proposed methods output similar results to that of the l₁-regularized maximum likelihood estimation for the aforementioned models. Numerical experiments reveal that our methods work well and they may be better than the l₁-regularization in generalization, parameter estimation, and model selection. © The Author(s) 2024.

关键词： Exponential family generalized linear regression Information geometry Sparse modeling

来源：评论

学校读者我要写书评

暂无评论

Association between exposure to a mixture of dichlorophenol and parabens and lung function in adults from NHANES, 2007-2012

引用

HEART & LUNG 2025年 72卷 32-41页

作者： Li, Xinwei Nie, Meiyun Yang, Keke Qi, Xiaodong Yang, Ling Tongji Univ Shanghai Peoples Hosp 4 Dept Geriatr 1279 Sanmen Rd Shanghai 200434 Peoples R China

Background: Few studies have examined the effects of dichlorophenol and parabens on lung function, with most focusing on individual chemicals. Objectives: This study analyzes the effects of these chemicals on single or mixed exposures on lung function in adults. Methods: We utilized data from the 2007-2012 National Health and Nutrition Examination Survey (NHANES), focusing on urinary levels of dichlorophenol, parabens, and lung function measures. The generalized linear regression (GLM), weighted quantile sum (WQS) regression, and Bayesian kernel machine regression (BKMR) models were applied to assess the impact of chemical exposure on lung function. Results: A total of 2,599 adults with complete data were included in the analysis. Detection rates exceeding 75 % for 2,5-Dichlorophenol (2,5-DCP), 2,4-Dichlorophenol (2,4-DCP), methyl paraben, and propyl paraben were observed. In GLMs, 2,5-DCP was significantly negatively associated with forced vital capacity (FVC) and forced expiratory volume in 1 s (FEV1), either as a continuous (FVC: beta =-0.012, 95 % CI =-0.018,-0.006;FEV1: beta =-0.010, 95 % CI =-0.017,-0.004) or quartile variable (FVC: beta =-0.027, 95 % CI =-0.039,-0.016;FEV1: beta =-0.024, 95 % CI =-0.036,-0.011). The WQS regression confirmed a negative effect of the chemical mixture on lung function, with significant associations for both FVC (beta =-0.013, 95 % CI =-0.018,-0.008) and FEV1 (beta =-0.013, 95 % CI =-0.017,-0.007). These results were consistent in BKMR models. Conclusion: Exposure to dichlorophenol and parabens, either individually or in combination, is associated with decreased lung function in humans.

关键词： Dichlorophenol Parabens Lung function generalized linear regression Weighted quantile sum regression Bayesian kernel machine regression

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Vehicle Delays at Midblock Rectangular Rapid Flashing Beacon and Pedestrian Hybrid Beacon Pedestrians' Crossings

引用

JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS 2025年第2期151卷

作者： Anwari, Nafis Abdel-Aty, Mohamed Ahsan, Md Jamil Manatee Cty Govt Transportat Planner 1112 Manatee Ave Bradenton FL 34205 USA Univ Cent Florida Dept Civil Environm & Construct Engn POB 16245012800 Pegasus DrSuite 211 Orlando FL 32816 USA

This study aims to evaluate and compare vehicle delay at two selected midblock rectangular rapid flashing beacon (RRFB) sites and five selected midblock pedestrian hybrid beacon (PHB) sites in Florida using video data collected during the study period of July to November 2021. Computer vision and data processing were used to calculate the average delay for each vehicle that interacted with a crossing pedestrian. The vehicle delays were then averaged separately for each lane and direction and for the combined directions, creating three data sets having total numbers of observations of 937, 618, and 441, respectively. Initial Mann-Whitney-Wilcoxon tests revealed significant differences in average delay values across different treatment types and periods for each of the three data sets. In addition, a generalized linear regression model considering various traffic and pedestrian factors revealed significant differences in vehicle delay across RRFB and PHB sites. PHB presence, weekend, signal activation, pedestrian crossing speed, vehicle speed, pedestrian starting position, traffic flow, and the afternoon/evening period have been found to be significant determinants of vehicle delay. The model results remained relatively stable when average delay was considered separately for each lane and direction;however, performance decreased when the delay was averaged for the combined directions of the roadway. The results suggest that vehicle delay increased at PHB sites compared to at RRFB sites, indicating a possible decrease in traffic efficiency at PHB sites.

关键词： Rectangular rapid flashing beacon Pedestrian hybrid beacon Vehicle delay Mann-Whitney-Wilcoxon tests generalized linear regression

来源：评论

学校读者我要写书评

暂无评论

Sequential Estimate for generalized linear Models with Uncertain Number of Effective Variables

引用

Journal of Systems Science & Complexity 2015年第2期28卷 424-438页

作者： LU Haibo WANG Zhanfeng WU Yaohua Department of Statistics and Finance University of Science and Technology of China

For the generalized linear model,the authors propose a sequential sampling procedure based on an adaptive shrinkage estimate of *** method can determine a minimum sample size under which effective variables contributing to the model are identified and estimates of regression parameters achieve the required *** authors prove that the proposed sequential procedure is asymptotically *** simulation studies show that the proposed method can save a large number of samples compared to the traditional sequential approach.

关键词： Confidence set generalized linear regression sequential sampling stopping rule

来源：评论

学校读者我要写书评

暂无评论

A machine learning and genetic algorithm-based method for predicting width deviation of hot-rolled strip in steel production systems

引用

INFORMATION SCIENCES 2022年 589卷 360-375页

作者： Ji, Yingjun Liu, Shixin Zhou, Mengchu Zhao, Ziyan Guo, Xiwang Qi, Liang Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA St Petersburg State Marine Tech Univ Dept Cyber Phys Syst Lotsmanskaya St 3 St Petersburg 198262 Russia Liaoning Shihua Univ Coll Comp & Commun Engn Fushun 113001 Peoples R China Shandong Univ Sci & Technol Dept Comp Sci & Technol Qingdao 266590 Peoples R China

Width deviation is an important metric for evaluating the quality of a hot-rolled strip in steel production systems. This paper considers a width deviation prediction problem and proposes a Machine-learning and Genetic-algorithm-based Hybrid method named MGH to obtain a prediction model. Existing work mainly focuses on high prediction accuracy, while ignoring interpretability. This work aims to build a prediction model that can make a good trade-off between two industry-required criteria, i.e., prediction accuracy and interpretability. It first collects some process variables in a hot rolling process and includes them as well as some constructed variables in a feature pool. Then we propose MGH to find representative variables from it and build a prediction model. MGH results from the integration of hierarchical clustering, genetic algorithm, and generalized linear regression. In detail, hierarchical clustering is applied to divide variables into clusters. Genetic algorithm and generalized linear regression are innovatively combined to select a representative variable from each cluster and develop a prediction model. The computational experiments conducted on both industrial and public datasets show that the proposed method can effectively balance prediction accuracy and interpretability of its resulting model. It has better overall performance than the compared state-of-the-art models. (C) 2021 Elsevier Inc. All rights reserved.

关键词： Feature construction generalized linear regression Genetic algorithm Hierarchical clustering Hot-rolled strip Width deviation prediction

来源：评论

学校读者我要写书评

暂无评论

Multivariate regression of mixed responses for evaluation of visualization designs

引用

IISE TRANSACTIONS 2020年第3期53卷 313-325页

作者： Kang, Xiaoning Chen, Xiaoyu Jin, Ran Wu, Hao Deng, Xinwei Dongbei Univ Finance & Econ Inst Supply Chain Analyt Dalian Peoples R China Dongbei Univ Finance & Econ Int Business Coll Dalian Peoples R China Virginia Tech Grado Dept Ind & Syst Engn Blacksburg VA USA Virginia Tech Discovery Analyt Ctr Blacksburg VA USA Virginia Tech Dept Stat Blacksburgh VA 24061 USA

Information visualization significantly enhances human perception by graphically representing complex data sets. The variety of visualization designs makes it challenging to efficiently evaluate all possible designs catering to users' preferences and characteristics. Most existing evaluation methods perform user studies to obtain multivariate qualitative responses from users via questionnaires and interviews. However, these methods cannot support online evaluation of designs, as they are often time-consuming. A statistical model is desired to predict users' preferences on visualization designs based on non-interference measurements (i.e., wearable sensor signals). In this work, we propose a Multivariate regression of Mixed Responses (MRMR) to facilitate quantitative evaluation of visualization designs. The proposed MRMR method is able to provide accurate model prediction with meaningful variable selection. A simulation study and a user study of evaluating visualization designs with 14 effective participants are conducted to illustrate the merits of the proposed model.

关键词： generalized linear regression GLASSO information visualization mixed responses quantitative evaluation wearable sensors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：