{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T02:42:28Z","timestamp":1791340948546,"version":"4.3.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["12301365"],"award-info":[{"award-number":["12301365"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2040000075"],"award-info":[{"award-number":["WK2040000075"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2040250139"],"award-info":[{"award-number":["WK2040250139"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>With advancements in data-collecting techniques, large-scale data have become increasingly prevalent in medical science. For instance, gene expression data provide information on tens of thousands of genes, while diagnostic imaging, such as the magnetic resonance imaging, generates a vast volume of pixels. While various sparse linear discriminant analysis methods have been developed to handle high-dimensional medical data, they often assume the light-tailed predictors, which is frequently violated in real applications. In this paper, we propose a robust classifier under an elliptically contoured discriminant analysis (EDA) model, which accommodates both light-tailed and heavy-tailed data. In addition, we assess the prediction accuracy using the balanced rate, a more appropriate metric when the data is imbalanced. Under the EDA model, we identify the intrinsic dimension-reduction subspace that captures all information from predictors for achieving the lowest balanced rate. By leveraging this dimension-reduction subspace, we propose a robust high-dimensional classifier, which reduces data dimensionality through subspace projection, followed by prediction on the reduced data. Theoretically, our proposal simultaneously enjoys the consistencies of subspace estimation, variable selection, and prediction accuracy under only finite fourth-moment condition of predictors. Numerically, we apply our method to synthetic data and three real datasets, including two lung cancer data and a leukemia data. The empirical findings support the superiority of our approach over other state-of-the-art methods.<\/jats:p>","DOI":"10.1093\/biomtc\/ujag039","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:46:55Z","timestamp":1770814015000},"source":"Crossref","is-referenced-by-count":1,"title":["Sparse robust discriminant analysis for high-dimensional and heavy-tailed data"],"prefix":"10.1093","volume":"82","author":[{"given":"Weijian","family":"Huang","sequence":"first","affiliation":[{"name":"Faculty of Business for Science & Technology, School of Management, University of Science and Technology of China , Hefei, Anhui 230026 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0563-5622","authenticated-orcid":false,"given":"Qing","family":"Mai","sequence":"additional","affiliation":[{"name":"Department of Statistics, Florida State University , Tallahassee, FL 32312 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4886-5682","authenticated-orcid":false,"given":"Jing","family":"Zeng","sequence":"additional","affiliation":[{"name":"Faculty of Business for Science & Technology, School of Management, University of Science and Technology of China , Hefei, Anhui 230026 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"2026022603344587800_bib1","doi-asserted-by":"crossref","first-page":"2676","DOI":"10.1016\/j.patcog.2015.02.016","article-title":"Generalized quadratic discriminant analysis","volume":"48","author":"Bose","year":"2015","journal-title":"Pattern Recognition"},{"key":"2026022603344587800_bib2","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"2026022603344587800_bib3","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1198\/jasa.2011.tm11199","article-title":"A direct estimation approach to sparse linear discriminant analysis","volume":"106","author":"Cai","year":"2011","journal-title":"Journal of the American Statistical Association"},{"key":"2026022603344587800_bib4","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1111\/rssb.12326","article-title":"High dimensional linear discriminant analysis: optimality, adaptive algorithm and missing data","volume":"81","author":"Cai","year":"2019","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"2026022603344587800_bib5","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1198\/TECH.2011.08118","article-title":"Sparse discriminant analysis","volume":"53","author":"Clemmensen","year":"2011","journal-title":"Technometrics"},{"key":"2026022603344587800_bib6","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Machine Learning"},{"key":"2026022603344587800_bib7","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1214\/07-AOS504","article-title":"High dimensional classification using features annealed independence rules","volume":"36","author":"Fan","year":"2008","journal-title":"The Annals of Statistics"},{"key":"2026022603344587800_bib8","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1214\/20-AOS1980","article-title":"A shrinkage principle for heavy-tailed data: High-dimensional robust low-rank matrix recovery","volume":"49","author":"Fan","year":"2021","journal-title":"The Annals of Statistics"},{"key":"2026022603344587800_bib9","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1111\/rssb.12001","article-title":"Tuning parameter selection in high dimensional penalized likelihood","volume":"75","author":"Fan","year":"2013","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"2026022603344587800_bib10","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","volume":"7","author":"Fisher","year":"1936","journal-title":"Annals of Eugenics"},{"key":"2026022603344587800_bib11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"Journal of Statistical Software"},{"key":"2026022603344587800_bib12","doi-asserted-by":"crossref","first-page":"107981","DOI":"10.1016\/j.patcog.2021.107981","article-title":"Robust generalised quadratic discriminant analysis","volume":"117","author":"Ghosh","year":"2021","journal-title":"Pattern Recognition"},{"key":"2026022603344587800_bib13","first-page":"4963","article-title":"Translation of microarray data into clinically relevant cancer diagnostic tests using gene expression ratios in lung cancer and mesothelioma","volume":"62","author":"Gordon","year":"2002","journal-title":"Cancer Research"},{"key":"2026022603344587800_bib14","doi-asserted-by":"crossref","first-page":"1597","DOI":"10.1198\/jasa.2009.tm08107","article-title":"Median-based classifiers for high-dimensional data","volume":"104","author":"Hall","year":"2009","journal-title":"Journal of the American Statistical Association"},{"key":"2026022603344587800_bib15","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1093\/biomet\/asw015","article-title":"Quantile-based classifiers","volume":"103","author":"Hennig","year":"2016","journal-title":"Biometrika"},{"key":"2026022603344587800_bib16","doi-asserted-by":"crossref","DOI":"10.1002\/9781118150740","volume-title":"Multivariate Statistical Simulation: A Guide to Selecting and Generating Continuous Multivariate Distributions. Wiley Series in Probability and Statistics","author":"Johnson","year":"1987"},{"key":"2026022603344587800_bib17","doi-asserted-by":"crossref","first-page":"4595","DOI":"10.1007\/s11831-021-09547-0","article-title":"Computational techniques and tools for omics data analysis: state-of-the-art, challenges, and future directions","volume":"28","author":"Kaur","year":"2021","journal-title":"Archives of Computational Methods in Engineering"},{"key":"2026022603344587800_bib18","first-page":"457","article-title":"Sparse quadratic discriminant analysis for high dimensional data","volume":"25","author":"Li","year":"2015","journal-title":"Statistica Sinica"},{"key":"2026022603344587800_bib19","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1007\/s10565-024-09848-7","article-title":"CD36 inhibition reduces non-small-cell lung cancer development through AKT-mTOR pathway","volume":"40","author":"Liu","year":"2024","journal-title":"Cell Biology and Toxicology"},{"key":"2026022603344587800_bib20","doi-asserted-by":"crossref","first-page":"e001878","DOI":"10.1136\/bmjresp-2023-001878","article-title":"Single-cell RNA-sequencing uncovers the dynamic changes of tumour immune microenvironment in advanced lung adenocarcinoma","volume":"10","author":"Lu","year":"2023","journal-title":"BMJ Open Respiratory Research"},{"key":"2026022603344587800_bib21","first-page":"97","article-title":"Multiclass sparse discriminant analysis","volume":"29","author":"Mai","year":"2019","journal-title":"Statistica Sinica"},{"key":"2026022603344587800_bib22","first-page":"3479","article-title":"Edge-group sparse PCA for network-guided high dimensional data analysis","volume":"34","author":"Min","year":"2018","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2026022603344587800_bib23","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1111\/j.1541-0420.2008.01017.x","article-title":"Adaptive weighted learning for unbalanced multicategory classification","volume":"65","author":"Qiao","year":"2009","journal-title":"Biometrics"},{"key":"2026022603344587800_bib24","doi-asserted-by":"crossref","first-page":"3343","DOI":"10.1214\/22-EJS2022","article-title":"The robust nearest shrunken centroids classifier for high-dimensional heavy-tailed data","volume":"16","author":"Ren","year":"2022","journal-title":"Electronic Journal of Statistics"},{"key":"2026022603344587800_bib25","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1214\/10-AOS870","article-title":"Sparse linear discriminant analysis by thresholding for high dimensional data","volume":"39","author":"Shao","year":"2011","journal-title":"The Annals of Statistics"},{"key":"2026022603344587800_bib26","doi-asserted-by":"crossref","first-page":"1177847","DOI":"10.3389\/fimmu.2023.1177847","article-title":"Identification of novel gene signature for lung adenocarcinoma by machine learning to predict immunotherapy and prognosis","volume":"14","author":"Shu","year":"2023","journal-title":"Frontiers in Immunology"},{"key":"2026022603344587800_bib27","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1080\/01621459.2024.2402567","article-title":"Neyman-Pearson multi-class classification via cost-sensitive learning","volume":"120","author":"Tian","year":"2025","journal-title":"Journal of the American Statistical Association"},{"key":"2026022603344587800_bib28","first-page":"1","article-title":"Neyman-Pearson classification: parametrics and sample size requirement","volume":"21","author":"Tong","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"2026022603344587800_bib29","doi-asserted-by":"crossref","first-page":"257","DOI":"10.32917\/hmj\/1206128025","article-title":"Discriminant analysis under elliptical populations","volume":"24","author":"Wakaki","year":"1994","journal-title":"Hiroshima Mathematical Journal"},{"key":"2026022603344587800_bib30","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1198\/016214507000000509","article-title":"Unified LASSO estimation by least squares approximation","volume":"102","author":"Wang","year":"2007","journal-title":"Journal of the American Statistical Association"},{"key":"2026022603344587800_bib31","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1111\/j.1467-9868.2008.00693.x","article-title":"Shrinkage tuning parameter selection with a diverging number of parameters","volume":"71","author":"Wang","year":"2009","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"2026022603344587800_bib32","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1093\/biomet\/asm053","article-title":"Tuning parameter selectors for the smoothly clipped absolute deviation method","volume":"94","author":"Wang","year":"2007","journal-title":"Biometrika"},{"key":"2026022603344587800_bib33","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1111\/j.1467-9868.2011.00783.x","article-title":"Penalized classification using Fisher\u2019s linear discriminant","volume":"73","author":"Witten","year":"2011","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"2026022603344587800_bib34","first-page":"1391","article-title":"Mode-based classifier: A robust and flexible discriminant analysis for high-dimensional data","volume":"35","author":"Xiong","year":"2025","journal-title":"Statistica Sinica"},{"key":"2026022603344587800_bib35","first-page":"1249","article-title":"An efficient convex formulation for reduced-rank linear discriminant analysis in high dimensions","volume":"33","author":"Zeng","year":"2023","journal-title":"Statistica Sinica"},{"key":"2026022603344587800_bib36","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1080\/00401706.2016.1272495","article-title":"Tensor envelope partial least-squares regression","volume":"59","author":"Zhang","year":"2017","journal-title":"Technometrics"},{"key":"2026022603344587800_bib37","first-page":"3268","article-title":"Taming heavy-tailed features by shrinkage","volume":"130","author":"Zhu","year":"2021","journal-title":"Proceedings of The 24th International Conference on Artificial Intelligence and Statistics"},{"key":"2026022603344587800_bib38","doi-asserted-by":"crossref","first-page":"2471","DOI":"10.2147\/CMAR.S232260","article-title":"Circular RNA Circ-ZNF609 promotes lung adenocarcinoma proliferation by modulating miR-1224-3p\/ETV1 signaling","volume":"12","author":"Zuo","year":"2020","journal-title":"Cancer Management and Research"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/1\/ujag039\/67124900\/ujag039.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/1\/ujag039\/67124900\/ujag039.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:35:00Z","timestamp":1772094900000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/doi\/10.1093\/biomtc\/ujag039\/8498964"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,6]]}},"URL":"https:\/\/doi.org\/10.1093\/biomtc\/ujag039","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,1,6]]},"article-number":"ujag039"}}