Variable Selection Methods Research Articles

Time varying effects in survival analysis: a novel data-driven method for drift identification and variable selection

In this paper we address the problem of survival models when high-dimensional panel data are available. We discuss two related issues: The first one concerns the issue of variable selection and the second one deals with the stability over time of such a selection, since presence of time dimension in survival data requires explicit treatment of evolving socio-economic context. We show how graphical models can serve two purposes. First they serve as the input for a first algorithm to to assess the temporal stability of the data: Secondly, allow the deployment of a second algorithm which partially automates the process of variable selection, while retaining the option to incorporate domain expertise in the process of empirical model-building. To put our proposed methodology to the test, we utilize a dataset comprising Italian firms funded in 2009 and we study the survival of these entities over the period of 10 years. In addition to revealing significant volatility in the set of variables explaining firm exit over the years, our novel methodology enables us to offer a more nuanced perspective than the conventional one regarding the critical roles played by traditional variables such as industrial sector, geographical location, and innovativeness in firm survival.

Effect of variable selection strategy on the predictive models for adverse pregnancy outcomes of pre-eclampsia: A retrospective study

Objectives: The improvement of prediction for adverse pregnancy outcomes is quite essential to the women suffering from pre-eclampsia, while the collection of predictive indicators is the prerequisite. The traditional knowledge-based strategy for variable selection confronts challenge referring to dataset with high-dimensional or unfamiliar data. In this study, we employed five different automatic variable selection methods to screen out influential indicators, and evaluated the performance of constructed predictive models. Methods: Seven hundreds and thirty-three Han-Chinese women were enrolled and 56 clinical and laboratory variables were recorded. After grouping based on binary pregnancy outcomes, statistical description and analysis were performed. Then, utilizing forward stepwise logistic regression (FSLR) as the reference method, another four variable selection strategies were included for filtering contributing variables as the predictive subsets, respectively. Finally, the logistic regression prediction models were constructed by the five subsets and evaluated by the receiver operator characteristic curve. Results: The variables confirmed statistical significance between the adverse and satisfactory outcomes groups did not overlap with the variables selected by selection strategies. “Platelet” and “Creatinine clearance rate” were the most influential indicator to predict adverse maternal outcome, while “Birth weight of neonates” was the best indicator for predicting adverse neonatal outcome. In average, the predictive models for neonatal outcomes achieved better performance than models for maternal outcomes. “Mutual information” and “Recursive feature elimination” were the best strategy under current dataset and study design. Conclusions: Variable selection strategies may provide an alternative approach besides picking influential indicators by statistical significance. Future work will focus on applying different variable selection methods to the high-dimensional dataset, which includes novel or unfamiliar variables. This aims to identify the most appropriate collection of predictors that can enhance prediction ability and clinical decision-making.

Martingale-residual-based greedy model averaging for high-dimensional current status data.

Current status data are a type of failure time data that arise when the failure time of study subject cannot be determined precisely but is known only to occur before or after a random monitoring time. Variable selection methods for the failure time data have been discussed extensively in the literature. However, the statistical inference of the model selected based on the variable selection method ignores the uncertainty caused by model selection. To enhance the prediction accuracy for risk quantities such as survival probability, we propose two optimal model averaging methods under semiparametric additive hazards models. Specifically, based on martingale residuals processes, a delete-one cross-validation (CV) process is defined, and two new CV functional criteria are derived for choosing model weights. Furthermore, we present a greedy algorithm for the implementation of the techniques, and the asymptotic optimality of the proposed model averaging approaches is established, along with the convergence of the greedy averaging algorithms. A series of simulation experiments demonstrate the effectiveness and superiority of the proposed methods. Finally, a real-data example is provided as an illustration.

Multifactor conditional equity premium model: Evidence from China's stock market

There is mixed evidence of a positive relationship between the stock market risk and return. We reexamine this critical implication of asset pricing theory using fresh data from China's stock market, which is largely segmented from the rest of the global financial market. Using formal variable selection methods and a comprehensive set of predictor variables, we identify conditional market variance, scaled market prices, and inflation as crucial determinants of equity premiums. The estimated simple risk-return relationship exhibits downward omitted variable bias, which underlines the importance of considering multiple factors to explain the variation in equity premiums. We cannot wholly attribute the three-factor conditional equity premium model to data mining, as Guo, Sanni, and Yu (2022) select the same model for the U.S. stock market. These findings challenge existing asset pricing models and provide valuable guidance for future theoretical research.

How authors select covariates in the multivariate analysis of cancer studies in 10 oncology journals in Korea: a descriptive study

Purpose: Cancer is the leading cause of death in Korea, leading many investigators to focus on cancer research. We present the current practice of variable selection methods for multivariate analyses in cancer studies recently published in major oncology journals in Korea.Methods: We included observational studies investigating associations between exposures and outcomes using multivariate analysis from 10 major oncology journals published in 2021 in KoreaMed, a Korean electronic database. Two reviewers independently and in duplicate performed the reference screening and data extraction. For each study included in this review, we collected important aspects of the variable selection methods in multivariate models, including the study characteristics, analytic methods, and covariate selection methods. The descriptive statistics of the data are presented.Results: In total, 107 studies were included. None used prespecified covariate selection methods, and half of the studies did not provide enough information to classify covariate selection methods. Among the studies reporting selection methods, almost all studies only used data-driven methods, despite having study questions related to causality. The most commonly used method for variable selection was significance in the univariate model, with the outcome as the dependent variable.Conclusion: Half of the included studies did not provide sufficient information to assess the variable selection method, and most used a limited data-driven method. We believe that the reporting of covariate selection methods requires improvement, and our results can be used to educate researchers, editors, and reviewers to increase the transparency and adequacy of covariate selection for multivariable analyses in observational studies.

Monthly Streamflow Prediction of the Source Region of the Yellow River Based on Long Short-Term Memory Considering Different Lagged Months

Accurate and reliable monthly streamflow prediction plays a crucial role in the scientific allocation and efficient utilization of water resources. In this paper, we proposed a prediction framework that integrates the input variable selection method and Long Short-Term Memory (LSTM). The input selection methods, including autocorrelation function (ACF), partial autocorrelation function (PACF), and time lag cross-correlation (TLCC), were used to analyze the lagged time between variables. Then, the performance of the LSTM model was compared with three other traditional methods. The framework was used to predict monthly streamflow at the Jimai, Maqu, and Tangnaihai stations in the source area of the Yellow River. The results indicated that grid search and cross-validation can improve the efficiency of determining model parameters. The models incorporating ACF, PACF, and TLCC with lagged time are evidently superior to the models using the current variable as the model inputs. Furthermore, the LSTM model, which considers the lagged time, demonstrated better performance in predicting monthly streamflow. The coefficient of determination (R2) improved by an average of 17.46%, 33.94%, and 15.29% for each station, respectively. The integrated framework shows promise in enhancing the accuracy of monthly streamflow prediction, thereby aiding in strategic decision-making for water resources management.

Simultaneous variable selection and estimation for survival data via the Gaussian seamless- penalty.

We propose a new simultaneous variable selection and estimation procedure with the Gaussian seamless- (GSELO) penalty for Cox proportional hazard model and additive hazards model. The GSELO procedure shows good potential to improve the existing variable selection methods by taking strength from both best subset selection (BSS) and regularization. In addition, we develop an iterative algorithm to implement the proposed procedure in a computationally efficient way. Theoretically, we establish the convergence properties of the algorithm and asymptotic theoretical properties of the proposed procedure. Since parameter tuning is crucial to the performance of the GSELO procedure, we also propose an extended Bayesian information criteria (EBIC) parameter selector for the GSELO procedure. Simulated and real data studies have demonstrated the prediction performance and effectiveness of the proposed method over several state-of-the-art methods.

Fault Diagnosis of Wastewater Treatment Processes Based on CPSO-DKPCA

The wastewater treatment process (WWTP) is one of the most common links in chemical plants. However, the testing for diagnosing faults in wastewater treatment plants is expensive and time-consuming. Due to strong nonlinearity and variable autocorrelation, traditional WWTP diagnostic methods based on principal component analysis (PCA) can lead to low fault detection rates (FDR) or difficulty in determining the root cause of faults. In this paper, an improved dynamic kernel principal component analysis (DKPCA) and Granger causality (GC) analysis model that uses chaotic particle swarm optimization (CPSO) to detect WWTP and locate the root causes of faults is proposed. First, a kernel function is introduced to map a nonlinear matrix to a linear space. Then, the training data are extended through a time lag constant to solve the problem of nonlinear and variable autocorrelation in WWTP. Moreover, a novel fault candidate variables selection method, together with GC, is introduced to locate the root variables of the fault. The CPSO algorithm is employed to optimize DKPCA's kernel function parameters, enhancing the accuracy of fault monitoring and diagnosis models. Compared with traditional methods, the proposed method has a better fault detection rate, achieving 95.83% and 93.33% fault detection rates in simulated and real WWTP, respectively.

Nonparametric estimation of linear personalized diagnostics rules via efficient grid algorithm.

Many diseases are heterogeneous, comprised of multiple disease subgroups. It is of great interest but highly unlikely to find a single biomarker that can accurately detect such heterogeneous diseases across different subgroups. In this article, we propose to estimate a personalized diagnostic rule (PDR) to tailor more effective biomarkers to each individual according to a linear combination of his or her profiles. A standard grid search algorithm can be used to estimate the optimal linear PDR that maximizes the area under the receiver operating characteristics curve (AUC) among all the linear PDRs, but it is time-consuming especially when the number of variables is large. Alternatively, we developed an efficient grid rotation algorithm that provides a nearly suboptimal solution and studied its variation to find the optimal solution. We implemented the cross-validated forward variable selection method to find a subset of useful variables while avoid overfitting. Extensive simulations show that our proposed method reduces bias and variance. Analysis of a gastric cancer biomarker study and censored survival outcome data illustrates the practical utility of our proposed method. The proposed method is implemented in the open-source R package persDx.

Strategies for the quality control of Chrysanthemi Flos: Rapid quantification and end-to-end fingerprint conversion based on FT-NIR spectroscopy.

Chrysanthemi Flos (CF) is widely used as a natural medicine or tea. Due to its diverse cultivation regions, CF exhibits varying quality. Therefore, the quality and swiftness in evaluation holds paramount significance for CF. The aim of the study was to construct a comprehensive evaluation strategy for assessing CF quality using HPLC, near-infrared (NIR) spectroscopy, and chemometrics, which included the rapid quantification analyses of chemical components and the Fourier transform (FT)-NIR to HPLC conversion of fingerprints. A total of 145 CF samples were utilised for data collection via NIR spectroscopy and HPLC. The partial least squares regression (PLSR) models were optimised using various spectral preprocessing and variable selection methods to predict the chemical composition content in CF. Both direct standardisation (DS) and PLSR algorithms were employed to establish the fingerprint conversion model from the FT-NIR spectrum to HPLC, and the model's performance was assessed through similarity and cluster analysis. The optimised PLSR quantitative models can effectively predict the content of eight chemical components in CF. Both DS and PLSR algorithms achieve the calibration conversion of CF fingerprints from FT-NIR to HPLC, and the predicted and measured HPLC fingerprints are highly similar. Notably, the best model relies on CF powder FT-NIR spectra and DS algorithm [root mean square error of prediction (RMSEP) = 2.7590, R2 = 0.8558]. A high average similarity (0.9184) prevails between predicted and measured fingerprints of test set samples, and the results of the clustering analysis exhibit a high level of consistency. This comprehensive strategy provides a novel and dependable approach for the rapid quality evaluation of CF.

Variable Selection for Hidden Markov Models with Continuous Variables and Missing Data

AbstractWe propose a variable selection method for multivariate hidden Markov models with continuous responses that are partially or completely missing at a given time occasion. Through this procedure, we achieve a dimensionality reduction by selecting the subset of the most informative responses for clustering individuals and simultaneously choosing the optimal number of these clusters corresponding to latent states. The approach is based on comparing different model specifications in terms of the subset of responses assumed to be dependent on the latent states, and it relies on a greedy search algorithm based on the Bayesian information criterion seen as an approximation of the Bayes factor. A suitable expectation-maximization algorithm is employed to obtain maximum likelihood estimates of the model parameters under the missing-at-random assumption. The proposal is illustrated via Monte Carlo simulation and an application where development indicators collected over eighteen years are selected, and countries are clustered into groups to evaluate their growth over time.

Evolutionary shift detection with ensemble variable selection

Abrupt environmental changes can lead to evolutionary shifts in trait evolution. Identifying these shifts is an important step in understanding the evolutionary history of phenotypes. The detection performances of different methods are influenced by many factors, including different numbers of shifts, shift sizes, where a shift occurs on a tree, and the types of phylogenetic structure. Furthermore, the model assumptions are oversimplified, so are likely to be violated in real data, which could cause the methods to fail. We perform simulations to assess the effect of these factors on the performance of shift detection methods. To make the comparisons more complete, we also propose an ensemble variable selection method (R package ELPASO) and compare it with existing methods (R packages ℓ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell$$\\end{document}1ou and PhylogeneticEM). The performances of methods are highly dependent on the selection criterion. ℓ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell$$\\end{document}1ou+pBIC is usually the most conservative method and it performs well when signal sizes are large. ℓ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell$$\\end{document}1ou+BIC is the least conservative method and it performs well when signal sizes are small. The ensemble method provides more balanced choices between those two methods. Moreover, the performances of all methods are heavily impacted by measurement error, tree reconstruction error and shifts in variance.

Probabilistic-Mechanistic Evaluation of a Hybrid Drying System Using l1 Norm Regularisation: Simultaneous Ohmic Heating and Convection Drying

Ohmic-assisted drying (OAD) is a novel drying system that combines ohmic heating and convection drying simultaneously. The present study is aimed at evaluating the mechanism of OAD system behaviours against the combined impact of operational and model uncertainties. Moreover, the dynamic (time-dependent), as well as static (end-of-drying) spatial homogeneity of the model predictions, was quantitatively described for the first time in the literature using Buzas and Gibson’s evenness value (an α-diversity index). The Monte Carlo simulation approach was used to propagate the uncertainty of randomly selected input variables using the Halton sequence sampling method. Mechanistic models include input uncertainties that lead to deviations in model estimations. Both time-dependent and independent global sensitivity of moisture, sample temperature, sample’s internal pressure, their spatial homogeneity, and drying time were assessed using Lasso regression (a variable selection method that penalises the coefficients using l1 norm). The stochastic results of the mechanistic investigation showed that the effects of the input variables are almost identical both as static and time-dependent variables. Lasso regression results indicated that operational and model uncertainties cause varying changes in the magnitude and direction of the stochastic model predictions throughout the process. By contrast, the homogeneity properties of the dry product are not caused by these variations and heterogeneous distribution of the electric field. Additionally, electrical conductivity, oven temperature, applied voltage, and initial moisture were found to be the variables which have the most significant effect on all the variables which were examined in terms of operational and model uncertainties. Practical Applications. The present study investigates the stochastic behaviour of the OAD system through the mechanistic model and using a probabilistic modelling approach. To the best of our knowledge, in addition to being the first study to probabilistically evaluate the OAD system, we are introducing Buzas and Gibson’s evenness value for the first time in the food science/technology literature. This measure serves as a numerical indicator of the spatial distribution homogeneity of the physical properties of the sample. The study’s findings and proposed methodologies will have further applications not only for researchers but also for manufacturers, particularly for those involved in the design and analysis of new drying and food systems in general. Moreover, the presented methods and novel homogeneity measures are generic tools; they can be easily adapted to other process improvement practices involving input/output uncertainty/variability.

Risk of papillary thyroid carcinoma and nodular goiter associated with exposure to semi-volatile organic compounds: A multi-pollutant assessment based on machine learning algorithms

BackgroundExposure to semi-volatile organic compounds (SVOCs) may link to thyroid nodule risk, but studies of mixed-SVOCs exposure effects are lacking. Traditional analytical methods are inadequate for dealing with mixed exposures, while machine learning (ML) seems to be a good way to fill the gaps in the field of environmental epidemiology research. ObjectivesDifferent ML algorithms were used to explore the relationship between mixed-SVOCs exposure and thyroid nodule. MethodsA 1:1:1 age- and gender-matched case-control study was conducted in which 96 serum SVOCs were measured in 50 papillary thyroid carcinoma (PTC), 50 nodular goiters (NG), and 50 controls. Different ML techniques such as Random Forest, AdaBoost were selected based on their predictive power, and variables were selected based on their weights in the models. Weighted quantile sum (WQS) regression and Bayesian kernel machine regression (BKMR) were used to assess the mixed effects of the SVOCs exposure on thyroid nodule. ResultsForty-three of 96 SVOCs with detection rate >80 % were included in the analysis. ML algorithms showed a consistent selection of SVOCs associated with thyroid nodule. Fluazifop-butyl and fenpropathrin are positively associated with PTC and NG in single compound models (all P < 0.05). WQS model shows that exposure to mixed-SVOCs was associated with an increased risk of PTC and NG, with the mixture dominated by fenpropathrin, followed by fluazifop-butyl and propham. In the BKMR model, mixtures showed a significant positive association with thyroid nodule risk at high exposure levels, and fluazifop-butyl showed positive effects associated with PTC and NG. ConclusionThis study confirms the feasibility of ML methods for variable selection in high-dimensional complex data and showed that mixed exposure to SVOCs was associated with increased risk of PTC and NG. The observed association was primarily driven by fluazifop-butyl and fenpropathrin. The findings warranted further investigation.

Robust Sparse Sufficient Dimension Reduction via Adaptive Lasso Penalty

In some multi-index models applications, there is an important role for dimension reduction and variable selection (VS) methods. The ALMAVE is a method for variables selection under sufficient dimension reduction theory settings. It combines the adaptive Lasso and MAVE (minimum average variance estimation) to produce sparse and accurate solutions. The ALMAVE is a very sensitive method to outliers in the response y due to use the least-squares criterion. In this article, we proposed robust ALMAVE. Also, an efficient estimation algorithm was proposed. The simulation studies and Logo design data analysis were employed to check the effectiveness of ALMAVE.

Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms.

Timely and accurate monitoring of soil salinity content (SSC) is essential for precise irrigation management of large-scale farmland. Uncrewed aerial vehicle (UAV) low-altitude remote sensing with high spatial and temporal resolution provides a scientific and effective technical means for SSC monitoring. Many existing soil salinity inversion models have only been tested by a single variable selection method or machine learning algorithm, and the influence of variable selection method combined with machine learning algorithm on the accuracy of soil salinity inversion remain further studied. Firstly, based on UAV multispectral remote sensing data, by extracting the spectral reflectance of each sampling point to construct 30 spectral indexes, and using the pearson correlation coefficient (PCC), gray relational analysis (GRA), variable projection importance (VIP), and support vector machine-recursive feature elimination (SVM-RFE) to screen spectral index and realize the selection of sensitive variables. Subsequently, screened and unscreened variables as model input independent variables, constructed 20 soil salinity inversion models based on the support vector machine regression (SVM), back propagation neural network (BPNN), extreme learning machine (ELM), and random forest (RF) machine learning algorithms, the aim is to explore the feasibility of different variable selection methods combined with machine learning algorithms in SSC inversion of crop-covered farmland. To evaluate the performance of the soil salinity inversion model, the determination coefficient (R2), root mean square error (RMSE) and performance deviation ratio (RPD) were used to evaluate the model performance, and determined the best variable selection method and soil salinity inversion model by taking alfalfa covered farmland in arid oasis irrigation areas of China as the research object. The variable selection combined with machine learning algorithm can significantly improve the accuracy of remote sensing inversion of soil salinity. The performance of the models has been improved markedly using the four variable selection methods, and the applicability varied among the four methods, the GRA variable selection method is suitable for SVM, BPNN, and ELM modeling, while the PCC method is suitable for RF modeling. The GRA-SVM is the best soil salinity inversion model in alfalfa cover farmland, with Rv 2 of 0.8888, RMSEv of 0.1780, and RPD of 1.8115 based on the model verification dataset, and the spatial distribution map of soil salinity can truly reflect the degree of soil salinization in the study area. Based on our findings, the variable selection combined with machine learning algorithm is an effective method to improve the accuracy of soil salinity remote sensing inversion, which provides a new approach for timely and accurate acquisition of crops covered farmland soil salinity information.

Predictive value of peri-chemotherapy hematological parameters for febrile neutropenia in patients with cancer.

The aim of this study was to compare hematological parameters pre- and early post-chemotherapy, and evaluate their values for predicting febrile neutropenia (FN). Patients diagnosed with malignant solid tumors receiving chemotherapy were included. Blood cell counts peri-chemotherapy and clinical information were retrieved from the hospital information system. We used the least absolute shrinkage and selection operator (LASSO) method for variable selection and fitted selected variables to a logistic model. We assessed the performance of the prediction model by the area under the ROC curve. The study population consisted of 4,130 patients with common solid tumors receiving a three-week chemotherapy regimen in Sichuan Cancer Hospital from February 2019 to March 2022. In the FN group, change percentage of neutrophil count decreased less (-0.02, CI: -0.88 to 3.48 vs. -0.04, CI: -0.83 to 2.24). Among hematological parameters, lower post-chemotherapy lymphocyte count (OR 0.942, CI: 0.934-0.949), change percentage of platelet (OR 0.965, CI: 0.955-0.975) and higher change percentage of post-chemotherapy neutrophil count (OR 1.015, CI: 1.011-1.018), and pre-chemotherapy NLR (OR 1.002, CI: 1.002-1.002) predicted an increased risk of FN. These factors improved the predicting model based on clinical factors alone. The AUC of the combination model was 0.8275. Peri-chemotherapy hematological markers improve the prediction of FN.

A hybrid variable selection method combining Fisher's linear discriminant combined population analysis and an improved binary cuckoo search algorithm.

In this paper, a novel hybrid variable selection method for model building by near-infrared (NIR) spectroscopy is proposed for composition measurement in industrial processes. A double-layer structure is designed for variable selection by combining Fisher's linear discriminant combined population analysis (FCPA) and an improved binary cuckoo search algorithm (IBCS). The Fisher classifier combined with model population analysis is used to select the variable interval wherein the useful variables are roughly located even when strong multicollinearity exists among spectral variables. Opposition-based learning (OBL) and jumping genes (JG) are introduced to improve the binary cuckoo search algorithm for the fine selection of key variables, thus avoiding the loss of excellent solutions due to randomness and the local optimum. Different variable selection methods were used to select variables for beer, corn, and diesel fuel datasets, and the partial least squares (PLS) algorithms were used to build calibration models to predict the original extract concentration of beer, the protein and starch content of corn, and the boiling point of diesel fuel, respectively. The results showed that the proposed PLS modeling method based on FCPA-IBCS has higher fitting accuracy and smaller prediction errors.

Evaluating variable selection methods for multivariable regression models: A simulation study protocol.

Researchers often perform data-driven variable selection when modeling the associations between an outcome and multiple independent variables in regression analysis. Variable selection may improve the interpretability, parsimony and/or predictive accuracy of a model. Yet variable selection can also have negative consequences, such as false exclusion of important variables or inclusion of noise variables, biased estimation of regression coefficients, underestimated standard errors and invalid confidence intervals, as well as model instability. While the potential advantages and disadvantages of variable selection have been discussed in the literature for decades, few large-scale simulation studies have neutrally compared data-driven variable selection methods with respect to their consequences for the resulting models. We present the protocol for a simulation study that will evaluate different variable selection methods: forward selection, stepwise forward selection, backward elimination, augmented backward elimination, univariable selection, univariable selection followed by backward elimination, and penalized likelihood approaches (Lasso, relaxed Lasso, adaptive Lasso). These methods will be compared with respect to false inclusion and/or exclusion of variables, consequences on bias and variance of the estimated regression coefficients, the validity of the confidence intervals for the coefficients, the accuracy of the estimated variable importance ranking, and the predictive performance of the selected models. We consider both linear and logistic regression in a low-dimensional setting (20 independent variables with 10 true predictors and 10 noise variables). The simulation will be based on real-world data from the National Health and Nutrition Examination Survey (NHANES). Publishing this study protocol ahead of performing the simulation increases transparency and allows integrating the perspective of other experts into the study design.

Characterization of the flavor profile of Hulatang using GC-IMS coupled with sensory analysis.

Hulatang is a traditional specialty snack in Henan, China, and is well known for its unique flavor. In this study, the volatile organic compounds (VOCs) in four kinds of Hulatang from two representative regions in Henan Province (Xiaoyaozhen and Beiwudu) were evaluated using headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS). The results showed that Xiaoyaozhen Hulatang exhibited more ethers, fewer terpenes and ketones than Beiwudu Hulatang. Additionally, Hulatang from different regions were classified using the orthogonal partial least squares-discriminant analysis (OPLS-DA) based on GC-IMS data. Twenty aroma substances were selected as the potential markers using the variable importance in the projection (VIP) variable selection method. Additionally, fifteen aroma components significantly contributing to the aroma of Hulatang were screened using the relative odor activity value (ROAV) (ROAV > 1). Combined with the sensory score results, twelve key substances with significant correlation with odor perception were selected. The flavor characteristics of the key substances revealed that the flavor of Hulatang was mainly composed of volatile components with camphor, green, almond, fatty, spicy, herbal, vegetable, fruity, floral, musty, and solvent aromas. Overall, the experimental results provide a theoretical basis for evaluating the flavor characteristics of Hulatang from different regions using GC-IMS.