A comparison of model choice strategies for logistic regression

Purpose:The purpose of this study is to develop and compare model choice strategies in context of logistic regression.Model choice means the choice of the covariates to be included in the model.Design/methodology/approach:The study is based on Monte Carlo simulations.The methods are compared in terms of three measures of accuracy:specificity and two kinds of sensitivity.A loss function combining sensitivity and specificity is introduced and used for a final comparison.Findings:The choice of method depends on how much the users emphasize sensitivity against specificity.It also depends on the sample size.For a typical logistic regression setting with a moderate sample size and a small to moderate effect size,either BIC,BICc or Lasso seems to be optimal.Research limitations:Numerical simulations cannot cover the whole range of data-generating processes occurring with real-world data.Thus,more simulations are needed.Practical implications:Researchers can refer to these results if they believe that their data-generating process is somewhat similar to some of the scenarios presented in this paper.Alternatively,they could run their own simulations and calculate the loss function.Originality/value:This is a systematic comparison of model choice algorithms and heuristics in context of logistic regression.The distinction between two types of sensitivity and a comparison based on a loss function are methodological novelties.

Composition Analysis and Identification of Ancient Glass Products Based on L1 Regularization Logistic Regression

In view of the composition analysis and identification of ancient glass products, L1 regularization, K-Means cluster analysis, elbow rule and other methods were comprehensively used to build logical regression, cluster analysis, hyper-parameter test and other models, and SPSS, Python and other tools were used to obtain the classification rules of glass products under different fluxes, sub classification under different chemical compositions, hyper-parameter K value test and rationality analysis. Research can provide theoretical support for the protection and restoration of ancient glass relics.

Integration of Multiple Spectral Data via a Logistic Regression Algorithm for Detection of Crop Residue Burned Areas:A Case Study of Songnen Plain,Northeast China

The burning of crop residues in fields is a significant global biomass burning activity which is a key element of the terrestrial carbon cycle,and an important source of atmospheric trace gasses and aerosols.Accurate estimation of cropland burned area is both crucial and challenging,especially for the small and fragmented burned scars in China.Here we developed an automated burned area mapping algorithm that was implemented using Sentinel-2 Multi Spectral Instrument(MSI)data and its effectiveness was tested taking Songnen Plain,Northeast China as a case using satellite image of 2020.We employed a logistic regression method for integrating multiple spectral data into a synthetic indicator,and compared the results with manually interpreted burned area reference maps and the Moderate-Resolution Imaging Spectroradiometer(MODIS)MCD64A1 burned area product.The overall accuracy of the single variable logistic regression was 77.38%to 86.90%and 73.47%to 97.14%for the 52TCQ and 51TYM cases,respectively.In comparison,the accuracy of the burned area map was improved to 87.14%and 98.33%for the 52TCQ and 51TYM cases,respectively by multiple variable logistic regression of Sentind-2 images.The balance of omission error and commission error was also improved.The integration of multiple spectral data combined with a logistic regression method proves to be effective for burned area detection,offering a highly automated process with an automatic threshold determination mechanism.This method exhibits excellent extensibility and flexibility taking the image tile as the operating unit.It is suitable for burned area detection at a regional scale and can also be implemented with other satellite data.

Utilization of Logistical Regression to the Modified Sine-Gordon Model in the MST Experiment

In this paper, a logistical regression statistical analysis (LR) is presented for a set of variables used in experimental measurements in reversed field pinch (RFP) machines, commonly known as “slinky mode” (SM), observed to travel around the torus in Madison Symmetric Torus (MST). The LR analysis is used to utilize the modified Sine-Gordon dynamic equation model to predict with high confidence whether the slinky mode will lock or not lock when compared to the experimentally measured motion of the slinky mode. It is observed that under certain conditions, the slinky mode “locks” at or near the intersection of poloidal and/or toroidal gaps in MST. However, locked mode cease to travel around the torus;while unlocked mode keeps traveling without a change in the energy, making it hard to determine an exact set of conditions to predict locking/unlocking behaviour. The significant key model parameters determined by LR analysis are shown to improve the Sine-Gordon model’s ability to determine the locking/unlocking of magnetohydrodyamic (MHD) modes. The LR analysis of measured variables provides high confidence in anticipating locking versus unlocking of slinky mode proven by relational comparisons between simulations and the experimentally measured motion of the slinky mode in MST.

Lasso-Logistic回归模型拟合临床因素、NF-κB/NLRP3信号通路预测心肌梗死后缺血性心肌病价值

目的基于Lasso-Logistic回归分析心肌梗死后缺血性心肌病(ICM)影响因素,探讨临床因素、核因子-κB(NF-κB)/核苷酸结合寡聚结构域样受体家族3(NLRP3)信号通路及Lasso-Logistic回归模型对心肌梗死后ICM的预测价值,为本病防治提供参考。方法选取2020年9月—2023年9月秦皇岛市第一医院收治的342例心肌梗死患者为研究对象进行前瞻性研究,按照7∶3比例分为建模组239例、验证组103例,依据经皮冠状动脉介入术(PCI)术后6个月内是否发生ICM分为ICM亚组、非ICM亚组。采用Lasso筛选心肌梗死后ICM发生相关变量,以有统计学意义变量构建临床因素模型,以NF-κB/NLRP3信号通路构建NF-κB/NLRP3信号通路模型,以临床因素、NF-κB/NLRP3联合建立混合模型(Lasso-Logistic回归模型)。对比不同预测模型对心肌梗死后ICM的预测价值。结果建模组ICM发生率为27.97%,验证组ICM发生率为26.47%;Lasso筛选出5个预测变量为NF-kB mRNA、NLRP3 mRNA、Gensini评分、LVEF、饮酒,Logistic回归分析显示,Gensini评分、NLRP3 mRNA、NF-κB mRNA、饮酒是心肌梗死后ICM影响因素(P<0.05);混合模型预测心肌梗死后ICM的AUC、敏感度、特异度分别为0.921、80.30%、88.82%,临床因素模型分别为0.886、78.79%、85.29%,NF-κB/NLRP3信号通路模型分别为0.873、74.24%、87.06%,混合模型的AUC高于临床因素模型、NF-κB/NLRP3信号通路模型(P<0.05)。结论Gensini评分、NLRP3 mRNA、NF-κB mRNA、饮酒是心肌梗死后ICM危险因素,联合上述影响因素建立Lasso-Logistic回归模型,该模型对心肌梗死后ICM具有一定预测效能,有助于临床早期筛查高危人群,并予以相应干预措施,以降低ICM发生风险。

Logistic Regression Trust–A Trust Model for Internet-of-Things Using Regression Analysis

Internet of Things(IoT)is a popular social network in which devices are virtually connected for communicating and sharing information.This is applied greatly in business enterprises and government sectors for delivering the services to their customers,clients and citizens.But,the interaction is success-ful only based on the trust that each device has on another.Thus trust is very much essential for a social network.As Internet of Things have access over sen-sitive information,it urges to many threats that lead data management to risk.This issue is addressed by trust management that help to take decision about trust-worthiness of requestor and provider before communication and sharing.Several trust-based systems are existing for different domain using Dynamic weight meth-od,Fuzzy classification,Bayes inference and very few Regression analysis for IoT.The proposed algorithm is based on Logistic Regression,which provide strong statistical background to trust prediction.To make our stand strong on regression support to trust,we have compared the performance with equivalent sound Bayes analysis using Beta distribution.The performance is studied in simu-lated IoT setup with Quality of Service(QoS)and Social parameters for the nodes.The proposed model performs better in terms of various metrics.An IoT connects heterogeneous devices such as tags and sensor devices for sharing of information and avail different application services.The most salient features of IoT system is to design it with scalability,extendibility,compatibility and resiliency against attack.The existing worksfinds a way to integrate direct and indirect trust to con-verge quickly and estimate the bias due to attacks in addition to the above features.

Diagnosis of Autism Spectrum Disorder by Imperialistic Competitive Algorithm and Logistic Regression Classifier

Autism spectrum disorder(ASD),classified as a developmental disability,is now more common in children than ever.A drastic increase in the rate of autism spectrum disorder in children worldwide demands early detection of autism in children.Parents can seek professional help for a better prognosis of the child’s therapy when ASD is diagnosed under five years.This research study aims to develop an automated tool for diagnosing autism in children.The computer-aided diagnosis tool for ASD detection is designed and developed by a novel methodology that includes data acquisition,feature selection,and classification phases.The most deterministic features are selected from the self-acquired dataset by novel feature selection methods before classification.The Imperialistic competitive algorithm(ICA)based on empires conquering colonies performs feature selection in this study.The performance of Logistic Regression(LR),Decision tree,K-Nearest Neighbor(KNN),and Random Forest(RF)classifiers are experimentally studied in this research work.The experimental results prove that the Logistic regression classifier exhibits the highest accuracy for the self-acquired dataset.The ASD detection is evaluated experimentally with the Least Absolute Shrinkage and Selection Operator(LASSO)feature selection method and different classifiers.The Exploratory Data Analysis(EDA)phase has uncovered crucial facts about the data,like the correlation of the features in the dataset with the class variable.

Weighted Maximum Likelihood Technique for Logistic Regression

In this paper, a weighted maximum likelihood technique (WMLT) for the logistic regression model is presented. This method depended on a weight function that is continuously adaptable using Mahalanobis distances for predictor variables. Under the model, the asymptotic consistency of the suggested estimator is demonstrated and properties of finite-sample are also investigated via simulation. In simulation studies and real data sets, it is observed that the newly proposed technique demonstrated the greatest performance among all estimators compared.

Application of Regularized Logistic Regression and Artificial Neural Network Model for Ozone Classification across El Paso County, Texas, United States

This paper focuses on ozone prediction in the atmosphere using a machine learning approach. We utilize air pollutant and meteorological variable datasets from the El Paso area to classify ozone levels as high or low. The LR and ANN algorithms are employed to train the datasets. The models demonstrate a remarkably high classification accuracy of 89.3% in predicting ozone levels on a given day. Evaluation metrics reveal that both the ANN and LR models exhibit accuracies of 89.3% and 88.4%, respectively. Additionally, the AUC values for both models are comparable, with the ANN achieving 95.4% and the LR obtaining 95.2%. The lower the cross-entropy loss (log loss), the higher the model’s accuracy or performance. Our ANN model yields a log loss of 3.74, while the LR model shows a log loss of 6.03. The prediction time for the ANN model is approximately 0.00 seconds, whereas the LR model takes 0.02 seconds. Our odds ratio analysis indicates that features such as “Solar radiation”, “Std. Dev. Wind Direction”, “outdoor temperature”, “dew point temperature”, and “PM10” contribute to high ozone levels in El Paso, Texas. Based on metrics such as accuracy, error rate, log loss, and prediction time, the ANN model proves to be faster and more suitable for ozone classification in the El Paso, Texas area.

Predictive Modeling for Analysis of Coronavirus Symptoms Using Logistic Regression

This paper presents a case study on the IPUMS NHIS database,which provides data from censuses and surveys on the health of the U.S.population,including data related to COVID-19.By addressing gaps in previous studies,we propose a machine learning approach to train predictive models for identifying and measuring factors that affect the severity of COVID-19 symptoms.Our experiments focus on four groups of factors:demographic,socio-economic,health condition,and related to COVID-19 vaccination.By analysing the sensitivity of the variables used to train the models and the VEC(variable effect characteristics)analysis on the variable values,we identify and measure importance of various factors that influence the severity of COVID-19 symptoms.

105例不孕症患者子宫输卵管造影结果影响因素的Logistic回归分析

目的探讨不孕症患者子宫输卵管造影结果发生异常的影响因素。方法选取2021年1月至2023年5月在湖南中医药大学第二附属医院妇科门诊就诊并接受X线子宫输卵管造影(X-ray hysterosalpingography,X-HSG)检查的105例不孕症患者,收集患者临床资料包括年龄、月经周期、不孕症类型、支原体感染史、衣原体感染史、淋病奈瑟球菌感染史、盆腔炎相关病史、输卵管相关病史等,并填写《中医体质调查问卷表》,采用Logistic回归方程分析不孕症患者X-HSG结果的影响因素。结果X-HSG结果异常与盆腔炎相关病史、输卵管相关病史、年龄、气郁质及湿热质呈正相关(P<0.05),与不孕症类型、月经周期规律与否无相关性(P>0.05)。多因素Logistic回归分析结果显示:不孕症类型、月经周期、气郁质、湿热质是HSG发生异常的危险因素(OR>1),年龄、盆腔炎相关病史、输卵管相关病史是HSG发生异常的保护因素(OR<1)。结论适龄生育、减少盆腔炎相关病史、减少输卵管相关病史、调畅情志、忌食肥甘厚味对于减少输卵管病理损伤引起的不孕症至关重要。

影响结核性胸腔积液并发胸膜增厚的非条件Logistic回归分析

目的探讨影响结核性胸腔积液并发胸膜增厚的相关危险因素。方法回顾性分析2019年1月至2021年3月广州市胸科医院呼吸内科收治的123例结核性胸腔积液患者的临床资料,统计患者胸膜增厚情况,采用单因素及非条件Logistic回归法分析患者胸膜增厚的影响因素。结果胸膜未增厚与胸膜增厚患者性别、年龄、肺结核、胸水分布、用力肺活量(FVC)、第1秒用力呼气容积(FVE1)/FVC、胸水腺苷脱氨酶(ADA)、血清ADA、胸水白细胞、胸水淋巴细胞、胸水中性粒细胞和淋巴细胞比例比较差异无统计学意义;胸膜未增厚与胸膜增厚患者胸水量、胸水吸收时间、FVE1、胸水乳酸脱氢酶(LDH)、血清LDH、胸水蛋白、血清蛋白比较差异有统计学意义(P<0.05)。Logistic回归分析结果显示,胸水量(中大量)、FVE1、胸水LDH、血清LDH、胸水蛋白及血清蛋白是胸膜增厚发生的危险因素(P<0.05)。结论结核性胸腔积液并发胸膜增厚是多因素作用的结果,胸水量、FVE1、胸水吸收时间、胸水LDH、血清LDH、胸水蛋白和血清蛋白与胸膜增厚的发生密切相关,建议临床予以密切监测并积极采取针对性干预措施。

卵圆孔未闭合并偏头痛患者头痛程度影响因素的logistic回归分析

目的分析卵圆孔未闭(PFO)合并偏头痛患者头痛程度影响因素的logistic回归分析。方法选取2022年1—12月商丘市第一人民医院就诊的100例PFO合并偏头痛患者作为研究对象,采用视觉模拟评分法(VAS)分为轻度头痛组(58例)和中重度疼痛组(42例),采用多因素logistic回归分析影响PFO合并偏头痛患者头痛程度的因素。结果单因素分析显示,轻度头痛组和中重度疼痛组吸烟史、高血压史、睡眠质量、情绪变化、PFO右向左分流量、PFO直径、PFO隧道长度及有无房间隔膨出瘤差异有统计学意义(P<0.05)。logistic多因素回归分析显示,吸烟史、高血压史、睡眠质量差、情绪变化、PFO右向左分流量大、PFO直径大、PFO隧道短及房间隔膨出瘤是影响PFO合并偏头痛患者头痛程度的影响因素(P<0.05)。结论吸烟史、高血压史、睡眠质量差、情绪变化、PFO右向左分流量大、PFO直径大、PFO隧道短及房间隔膨出瘤可影响PFO合并偏头痛患者头痛程度,临床应根据上述因素进行针对性干预,以缓解偏头痛患者头痛程度。

社会融合视角下农民工城市定居意愿探赜——基于Logistic模型的实证研究

农民工的城市定居意愿影响农民工市民化进程,进而影响我国新型城镇化建设与乡村振兴。文章基于2023年873份农民工问卷,在社会融合视角下,构建二元logistic回归模型对农民工的城市定居意愿影响因素进行研究。实证研究表明,只有58%的农民工具有城市定居意愿。农民工性别、年龄、婚姻状况、教育水平、家庭随迁人口数量、城市迁移时间长短等因素对定居意愿均没有显著影响;参加本地医保、身份认同、经济收入、健康状况、承包地等因素对农民工的城市定居意愿影响较大;社会参与度、闲暇生活、居住证等在一定程度上提升农民工的定居意愿。如何持续提升农民工的城市定居意愿,文章从社会关系融合、经济收入及公共服务均等化等三个方面提出了对策建议。

基于Logistic回归的国际时尚品牌销售渠道选择影响因素分析

为了帮助国际时尚品牌合理、科学地选择销售渠道和制定销售策略,以满足不同地区不同类型消费者的需求,提高品牌市场竞争力。首先依据访谈数据确定分析因子,建立影响国际时尚品牌销售渠道选择的多因素分析理论模型,提出可能影响国际品牌销售渠道选择的消费者偏好分析指标体系,从消费者个人特征、心理偏好、品类偏好以及时尚认知4个维度设计问卷并进行调研。运用SPSS软件对问卷回收数据进行录入,并采用Logistic回归分析数据,从而验证模型假设。通过分析结果可知,以上4个维度下的诸多影响因子均对国际品牌销售渠道的选择产生显著影响,并给出了具体的指导策略。品牌商可以根据研究结果制定对应的销售策略,以有效提高销售渠道利用率,最大化提升品牌销售业绩。

贝叶斯Logistic回归模型在中老年人心脏病影响因素分析中的应用

目的探讨贝叶斯Logistic回归模型在心脏病影响因素分析研究中的应用价值。方法数据资料来自2015年中国健康与养老追踪调查中的525例调查对象。利用OpenBUGS软件分别拟合了贝叶斯随机效应和固定效应的Logistic回归模型,并在两种模型中估计各影响因素与因变量关系的优势比(OR)及95%可信区间(95%CI)。结果贝叶斯随机效应和固定效应的Logistic回归模型分析结果均显示,性别、高血压和糖尿病是心脏病患病率的影响因素。两个模型的收敛效果均较好,参数估计结果也相差较小,但随机效应模型的拟合效果略差于固定效应模型(随机效应模型:DIC=156.6,pD=11.96;固定效应模型:DIC=155.8,pD=7.79)。结论在贝叶斯Logistic回归模型中引入随机效应参数需根据具体情况而定,否则反而可能会降低模型的拟合效果。

大学生“慢就业”现象及其影响因素——基于二元Logistic回归模型的实证研究

通过对32所高校调研分析发现,大学生“慢就业”现象呈现上升态势。研究表明:个人最高学历、职业规划清晰程度、就业主动性、父母对于子女选择“慢就业”的态度、是否为独生子女、家庭人均年收入、学校层次、学校就业指导服务质量等因素均显著影响大学生对于“慢就业”行为的认知与选择。为此,必须结合大学生“慢就业”行为选择的影响因素,开展“广谱式”的职业生涯规划教育、构建家校联合的就业指导机制、形成具有强针对性的就业指导体系。

影响阳虚体质因素的Logistic回归分析

目的:研究影响阳虚体质的主要因素。方法:采用横断面调查,收集上海中医药大学附属岳阳中西医结合医院治未病中心2020年9月至2021年11月中医体质调查数据。中医体质调查采用中医体质辨识软件V3.0实施,运用多因素Logistic回归模型分析筛选影响阳虚体质的主要因素。结果:共纳入811例研究对象,其中阳虚质211例(26.0%)。多因素Logistic回归分析结果显示,相对女性,男性阳虚质比例降低,差异具有统计学意义[OR=0.55,95%CI(0.37~0.81),P=0.002];相对年龄<50岁,年龄≥50岁者阳虚质比例较高,差异具有统计学意义[OR=1.83,95%CI(1.26~2.65),P=0.001];体质量超重、肥胖人群阳虚质比例高于体质量正常及偏低人群,差异具有统计学意义[OR=0.59,95%CI(0.38~0.91),P=0.018];高脂血症患者阳虚质比例高于血脂正常人群,差异具有统计学意义[OR=0.63,95%CI(0.44~0.90),P=0.011];脂肪性肝病患者阳虚质比例高于正常人群,差异具有统计学意义[OR=0.56,95%CI(0.37~0.87),P=0.010];功能性胃肠病阳虚质比例高于正常人群,差异具有统计学意义[OR=1.77,95%CI(1.05~2.99),P=0.032]。结论:年龄、性别、超重/肥胖、功能性胃肠病、脂肪性肝病、高脂血症是影响阳虚质的主要因素。

基于Logistic回归和支持向量机的早发性结直肠癌风险预测模型

目的:通过Logis tic回归和支持向量机(SVM)探究早发性结直肠癌(EOCRC)和晚发性结直肠癌(LOCRC)的危险因素,建立针对不同年龄段人群的风险预测模型并比较预测效果。方法:选择2012—2022年诊断为结直肠癌患者,记录人口学特征、临床表现、既往史、家族史、生活方式、体格检查、实验室检查及病理诊断,分别建立风险预测模型,比较两模型的ROC曲线下面积(AUROC)、准确率、精确率、召回率、F1分数。结果:综合两模型结果,EOCRC风险与出现消化道出血、腹胀腹痛、大便习惯改变等临床表现、体重减轻、肿瘤标志物升高具有较强的正相关性,与婚姻状况、阑尾切除史、糖尿病史、血脂异常病史、结直肠癌家族史也存在较弱的正相关;LOCRC风险与婚姻状况、出现临床表现、体重减轻、血脂异常、肿瘤标志物升高具有较强的正相关性,与年龄、吸烟、阑尾切除史、结直肠癌家族史也存在一定的正相关性。两模型的AUROC、准确率、F1分数相差不大,但Logistic回归模型的精确率更高而SVM模型的召回率更高。结论:EOCRC和LOCRC的危险因素不完全相同,婚姻状况、吸烟、血脂异常、肿瘤家族史在EOCRC中的贡献低于在LOCRC中的贡献。相较Logistic回归,SVM能发现更多的结直肠癌危险因素,能尽可能多的找出结直肠癌的可能患者。

Logistic Regression在我国河流水系氮污染研究中的应用

对四川省岷江、沱江及嘉陵江流域和江西省的赣江流域及鄱阳湖地区共 1 70多个水文站的数据进行了相关分析和多元回归分析 .结果表明 ,河流水中硝态氮浓度与年降雨量、人口密度、氮肥施用量、牲畜饲养量、农作物及粮食作物种植面积等因素有较好的相关性 .以以上数据资料为基础 ,将河流水NO3- N的浓度划分为背景浓度 (<0 7mg/L)、受人类活动的显著影响的NO3- N浓度 (>3 0mg/L)以及中间类 (0 7— 3 0mg/L)进行LogisticRegression分析 ,两个Logistic模型的准确度分别达 82 46%和 89 1 9% .运用Logistic模型对整个长江流域河流水中NO3- N浓度进行估计 ,结果与实测值基本相符合 .