{"id":"W4316928465","doi":"10.1371/journal.pone.0280258","title":"Stable variable ranking and selection in regularized logistic regression for severely imbalanced big binary data","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Resources Canada; Canada First Research Excellence Fund; University of Guelph","keywords":"Lasso (programming language); Covariate; Feature selection; Regularization (linguistics); Logistic regression; Ranking (information retrieval); Computer science; Regression; Statistics; Artificial intelligence; Elastic net regularization; Mathematics; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01196229,0.001098157,0.002049999,0.001210209,0.0007504356,0.001406393,0.002577438,0.001179298,0.001256677],"category_scores_gemma":[0.02506835,0.0007409612,0.001593229,0.001559291,0.001292553,0.001260303,0.002403537,0.002162579,0.0006991779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006760323,"about_ca_system_score_gemma":0.001905878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001956596,"about_ca_topic_score_gemma":0.002341861,"domain_scores_codex":[0.9928772,0.004769806,0.0002281772,0.0009455743,0.0009004265,0.0002786973],"domain_scores_gemma":[0.9883612,0.007618261,0.001278841,0.001529327,0.000882093,0.000330287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004756167,0.0002095521,0.009210123,0.0002654343,0.0003578878,0.0004931669,0.0002909912,0.7331021,0.004391262,0.04154944,0.004855078,0.2047994],"study_design_scores_gemma":[0.00004313915,0.00006296799,0.0004787179,0.0000108653,0.00001585383,0.0000493897,0.00001584698,0.9820219,0.0006465663,0.01589306,0.0007470892,0.00001463059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008170043,0.0001073532,0.9908658,0.000196704,0.00001823281,0.0000471999,0.00006221665,0.0003668212,0.0001656298],"genre_scores_gemma":[0.2916013,0.000241322,0.7047402,0.0003994801,0.0002088396,0.0004822145,0.0007474093,0.0002390135,0.001340275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01196229,"threshold_uncertainty_score":0.06326336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.384482777303951,"score_gpt":0.3883370557277064,"score_spread":0.003854278423755408,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}