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.

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.

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.

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.

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.

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.

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.

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.

Evaluation of Inference Adequacy in Cumulative Logistic Regression Models:An Empirical Validation of ISW-Ridge Relationships

Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p 〈0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions p^1, p^2 and p^3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to cheek the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height （X1 ） and potential energy （X2 ） significantly impact （p 〈 0. 0001 ） the amplitude-based refleeted rate; the P-values for the deviance and Pearson are all 〉 0.05 （0.2839, 0.3438, respectively）. That is, the goodness-of-fit between ridge height （ X1 ） and potential energy （X2） can further predict parameters under the scenario of the best parsimonious model. Investigation of 6 predictive powers （ R2, Max-rescaled R^2, Sorners＇ D, Gamma, Tau-a, and c, respectively） indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model.

Integrating vegetation indices and geo-environmental factors in GIS-based landslide-susceptibility mapping:using logistic regression

This study aimed to assess the potential of in-situ measured soil and vegetation characteristics in landslide susceptibility analyses.First,data for eight independent variables,i.e.,soil moisture content,soil organic content,compaction of soil(soil toughness),plant root strength,crop biomass,tree diameter at knee height,Shannon Wiener Index(SWI)for trees and herbs was assembled from field tests at two historic landslide locations:Aranayaka and Kurukudegama,Sri Lanka.An economical,finer resolution database was obtained as the field tests were not cost-prohibitive.The logistic regression(LR)analysis showed that soil moisture content,compaction of soil,SWI for trees and herbs were statistically significant at P<0.05.The variance inflation factors(VIFs)were computed to test for multicollinearity.VIF values(<2)confirmed the absence of multicollinearity between four independent variables in the LR model.Receiver Operating Characteristics(ROC)curve and Confusion Metrix(CM)methods were used to validate the model.In ROC analysis,areas under the curve of Success Rate Curve and Prediction Rate Curve were 84.5% and 96.6%,respectively,demonstrating the model’s excellent compatibility and predictability.According to the CM,the model demonstrated a 79.6% accuracy,63.6% precision,100% recall,and a F-measure of 77.8%.The model coefficients revealed that the vegetation cover has a more significant contribution to landslide susceptibility than soil characteristics.Finally,the susceptibility map,which was then classified as low,medium,and highly susceptible areas based on the natural breaks(Jenks)method,was generated using geographical information systems(GIS)techniques.All the historic landslide locations fell into the high susceptibility areas.Thus,validation of the model and inspection of the susceptibility map indicated that the in-situ soil and vegetation characteristics used in the model could be employed to demarcate historical landslide patches and identify landslide susceptible locations with high confidence.

Impacts of anthropogenic and biophysical factors on ecological land using logistic regression and random forest:A case study in Mentougou District,Beijing,China

Ecological land is an important guarantee to maintain urban ecological security and sustainable development.Although increasing studies have been brought to ecological land,with few explorations of the relative importance of anthropogenic-natural factors and how they interact to induce the ecological land evolution.This research sought to fill this gap.In this study,18 factors,including the risk of goaf collapse,fault,prime croplands,were selected from six aspects of topography,geology,climate,accessibility,socio-economic and land control policies.logistic regression(LR)and random forest(RF)models were adopted to identify the anthropogenic and biophysical factors on the dynamic change of ecological land of Mentougou in Beijing from 1990 to 2018.The results show that there was a significant increase in ecological land from 1990 to 2018.The increased area of ecological land reached 102.11 km2 with an increased rate of 0.78,the gravity center of ecological land gradually moved to the northwest.The impact of anthropogenic factors on ecological land was greater than that of natural factors,ecological land was mainly driven by proportion of prime cropland,per capita GDP,land urbanization,temperature,per capita rural income,elevation and aspect factors.Additionally,slope and precipitation were also identified as important predictors for ecological land change.The model comparison suggested that RF can better identify the relationship between ecological land and explanatory variables than LR model.Based on our findings,the implementation of government policies along with anthropogenic factors are the most important variables influencing ecological land change,and the rational planning and allocation of ecological land by Mentougou government are still needed.

An Investigation of Landslide Susceptibility Using Logistic Regression and Statistical Index Methods in Dailekh District, Nepal

Landslide distribution and susceptibility mapping are the fundamental steps for landslide-related hazard and disaster risk management activities, especially in the Himalaya region which has resulted in a great deal of death and damage to property. To better understand the landslide condition in the Nepal Himalaya, we carried out an investigation on the landslide distribution and susceptibility using the landslide inventory data and 12 different contributing factors in the Dailekh district, Western Nepal. Based on the evaluation of the frequency distribution of the landslide, the relationship between the landslide and the various contributing factors was determined.Then, the landslide susceptibility was calculated using logistic regression and statistical index methods along with different topographic(slope, aspect, relative relief, plan curvature, altitude, topographic wetness index) and non-topographic factors(distance from river, normalized difference vegetation index(NDVI), distance from road, precipitation, land use and land cover, and geology), and 470(70%) of total 658 landslides. The receiver operating characteristic(ROC) curve analysis using 198(30%) of total landslides showed that the prediction curve rates(area under the curve, AUC) values for two methods(logistic regression and statistical index) were 0.826, and 0.823with success rates of 0.793, and 0.811, respectively. The values of R-Index for the logistic regression and statistical index methods were83.66 and 88.54, respectively, consisting of high susceptible hazard classes. In general, this research concluded that the cohesive and coherent natural interplay of topographic and non-topographic factors strongly affects landslide occurrence, distribution, and susceptibility condition in the Nepal Himalaya region. Furthermore, the reliability of these two methods is verified for landslide susceptibility mapping in Nepal’s central mountain region.

WEIGHTED LASSO ESTIMATES FOR SPARSE LOGISTIC REGRESSION:NON-ASYMPTOTIC PROPERTIES WITH MEASUREMENT ERRORS

For high-dimensional models with a focus on classification performance,the?1-penalized logistic regression is becoming important and popular.However,the Lasso estimates could be problematic when penalties of different coefficients are all the same and not related to the data.We propose two types of weighted Lasso estimates,depending upon covariates determined by the Mc Diarmid inequality.Given sample size n and a dimension of covariates p,the finite sample behavior of our proposed method with a diverging number of predictors is illustrated by non-asymptotic oracle inequalities such as the?1-estimation error and the squared prediction error of the unknown parameters.We compare the performance of our method with that of former weighted estimates on simulated data,then apply it to do real data analysis.

Comparison of dimension reduction-based logistic regression models for case-control genome-wide association study:principal components analysis vs.partial least squares

With recent advances in biotechnology, genome-wide association study （GWAS） has been widely used to identify genetic variants that underlie human complex diseases and traits. In case-control GWAS, typical statistical strategy is traditional logistical regression （LR） based on single-locus analysis. However, such a single-locus analysis leads to the well-known multiplicity problem, with a risk of inflating type I error and reducing power. Dimension reduction-based techniques, such as principal component-based logistic regression （PC-LR）, partial least squares-based logistic regression （PLS-LR）, have recently gained much attention in the analysis of high dimensional genomic data. However, the perfor- mance of these methods is still not clear, especially in GWAS. We conducted simulations and real data application to compare the type I error and power of PC-LR, PLS-LR and LR applicable to GWAS within a defined single nucleotide polymorphism （SNP） set region. We found that PC-LR and PLS can reasonably control type I error under null hypothesis. On contrast, LR, which is corrected by Bonferroni method, was more conserved in all simulation settings. In particular, we found that PC-LR and PLS-LR had comparable power and they both outperformed LR, especially when the causal SNP was in high linkage disequilibrium with genotyped ones and with a small effective size in simulation. Based on SNP set analysis, we applied all three methods to analyze non-small cell lung cancer GWAS data.

Risk factors and prediction of acute kidney injury after liver transplantation:Logistic regression and artificial neural network approaches

BACKGROUND Acute kidney injury(AKI)has serious consequences on the prognosis of patients undergoing liver transplantation.Recently,artificial neural network(ANN)was reported to have better predictive ability than the classical logistic regression(LR)for this postoperative outcome.AIM To identify the risk factors of AKI after deceased-donor liver transplantation(DDLT)and compare the prediction performance of ANN with that of LR for this complication.METHODS Adult patients with no evidence of end-stage kidney dysfunction(KD)who underwent the first DDLT according to model for end-stage liver disease(MELD)score allocation system was evaluated.AKI was defined according to the International Club of Ascites criteria,and potential predictors of postoperative AKI were identified by LR.The prediction performance of both ANN and LR was tested.RESULTS The incidence of AKI was 60.6%(n=88/145)and the following predictors were identified by LR:MELD score>25(odds ratio[OR]=1.999),preoperative kidney dysfunction(OR=1.279),extended criteria donors(OR=1.191),intraoperative arterial hypotension(OR=1.935),intraoperative massive blood transfusion(MBT)(OR=1.830),and postoperative serum lactate(SL)(OR=2.001).The area under the receiver-operating characteristic curve was best for ANN(0.81,95%confidence interval[CI]:0.75-0.83)than for LR(0.71,95%CI:0.67-0.76).The root-mean-square error and mean absolute error in the ANN model were 0.47 and 0.38,respectively.CONCLUSION The severity of liver disease,pre-existing kidney dysfunction,marginal grafts,hemodynamic instability,MBT,and SL are predictors of postoperative AKI,and ANN has better prediction performance than LR in this scenario.

Regional Integrated Meteorological Forecasting and Warning Model for Geological Hazards Based on Logistic Regression

Information model is adopted to integrate factors of various geosciences to estimate the susceptibility of geological hazards. Further combining the dynamic rainfall observations, Logistic regression is used for modeling the probabilities of geological hazard occurrences, upon which hierarchical warnings for rainfall-induced geological hazards are produced. The forecasting and warning model takes numerical precipitation forecasts on grid points as its dynamic input, forecasts the probabilities of geological hazard occurrences on the same grid, and translates the results into likelihoods in the form of a 5-level hierarchy. Validation of the model with observational data for the year 2004 shows that 80% of the geological hazards of the year have been identified as ＂likely enough to release warning messages＂. The model can satisfy the requirements of an operational warning system, thus is an effective way to improve the meteorological warnings for geological hazards.

Spatial modelling of deforestation in Romanian Carpathian Mountains using GIS and Logistic Regression

Deforestation process represents a wide concern mainly in the mountain environments due to its role in global warming, biodiversity loss, land degradation and natural hazards occurrence. Thus, the present study is focused on the largest afforested landform unit of Romania and, consequently, the most affected area by forest losses: Carpathian Mountains. The main goal of the paper is to examine and analyze the various explanatory variables associated with deforestation process and to model the probability of deforestation using GIS spatial analysis and logistic regression. The forest cover for 1990 and 2012, derived from CORINE Land Cover(CLC) database, were used to quantify historical forest cover change included in the modelling. To explain the biophysical and anthropogenic effects, this study considered several explanatory factors related to local topography, forest cover pattern, accessibility, urban growth and population density. Using ROC(Receiver Operating Characteristic) and 500 controlling sampling points, the statistical and spatial validations were assessed in order to evaluate the performance of the resulted data. The analysis showed that the area experienced a continuous forest cover change, leading to the loss of over 250,000 ha of forested area during the period 1990–2012. The most significant influence of the explanatory factors of deforestation were noticed in case of distance to forest edge(β=–4.215), forest fragmentation(β=2.231), slope declivity(β=–1.901), elevation(β=1.734) and distance to roads(β=–1.713). The statistical and spatial validation indicates a good accuracy of the model with reasonably AUC(0.736) and Kappa(0.739) values. The model's results suggest an intensification of the deforestation process in the area, designing numerous new clusters with high probability in the Apuseni Mountains, northern and central part of the Eastern Carpathians, western part of the Southern Carpathians and northern part of the Banat Mountains. The study could represent a useful outcome to identify the forests more vulnerable to logging and to adopt appropriate policies and decisions in forest management and conservation. In addition, the resulted probability map could be used in other studies in order to investigate potential environmental implications(e.g. geomorphological hazards or impact on biodiversity and landscape diversity).

Logistic Regression Analysis on Factors Affecting Adoption of Rice-Fish Farming in North Iran

We evaluated the factors influencing the adoption of rice-fish farming in the Tavalesh region near the Caspian Sea in northern Iran. We conducted a survey with open-ended questions. Data were collected from 184 respondents （61 adopters and 123 non-adopters） randomly sampled from selected villages and analyzed using logistic regression and multi- response analysis. Family size, number of contacts with an extension agent, participation in extension-education activities, membership in social institutions and the presence of farm workers were the most important socio-economic factors for the adoption of rice-fish farming system. In addition, economic problems were the most common issue reported by adopters. Other issues such as lack of access to appropriate fish food, losses of fish, lack of access to high quality fish fingerlings and dehydration and poor water quality were also important to a number of farmers.

Application of a Novel Method for Machine Performance Degradation Assessment Based on Gaussian Mixture Model and Logistic Regression

The currently prevalent machine performance degradation assessment techniques involve estimating a machine＇s current condition based upon the recognition of indications of failure features,which entail complete data collected in different conditions.However,failure data are always hard to acquire,thus making those techniques hard to be applied.In this paper,a novel method which does not need failure history data is introduced.Wavelet packet decomposition（WPD） is used to extract features from raw signals,principal component analysis（PCA） is utilized to reduce feature dimensions,and Gaussian mixture model（GMM） is then applied to approximate the feature space distributions.Single-channel confidence value（SCV） is calculated by the overlap between GMM of the monitoring condition and that of the normal condition,which can indicate the performance of single-channel.Furthermore,multi-channel confidence value（MCV）,which can be deemed as the overall performance index of multi-channel,is calculated via logistic regression（LR） and that the task of decision-level sensor fusion is also completed.Both SCV and MCV can serve as the basis on which proactive maintenance measures can be taken,thus preventing machine breakdown.The method has been adopted to assess the performance of the turbine of a centrifugal compressor in a factory of Petro-China,and the result shows that it can effectively complete this task.The proposed method has engineering significance for machine performance degradation assessment.

利用Logistic Regression建立贷款申请最大化利润模型

随着金融证券化的发展,银行已由卖方市场转到了买方市场。因此,争夺实力雄厚、信用度高、还款能力强的客户是商业银行主要的竞争。文章综述了利用人工智能方法在贷款申请预测方面的研究。将利用Logistic Regression算法建立贷款申请最大化利润模型,同时利用机器学习的基本理论,证明本模型的泛化性良好。