{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001065516,0.0001045047,0.0003135668,0.00009412417,0.0000940039,0.00003519173,0.0001442763,0.00008349471,0.00003584688],"category_scores_gemma":[0.006062062,0.00008960544,0.000009309786,0.0004187469,0.00003052724,0.0000822299,0.0001599041,0.0001278881,0.000004619776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003024468,"about_ca_system_score_gemma":0.000045553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003376754,"about_ca_topic_score_gemma":0.000008859389,"domain_scores_codex":[0.9988841,0.0001143589,0.0002457348,0.0003184903,0.0001807371,0.0002565462],"domain_scores_gemma":[0.9974139,0.002155831,0.0000851451,0.0002328254,0.00006852525,0.00004379464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001948139,0.003338811,0.006526454,0.006929146,0.0003949532,0.00003922553,0.0006067584,0.0000289519,0.6991963,0.2558879,0.006519938,0.01858343],"study_design_scores_gemma":[0.001370222,0.0001844066,0.003304092,0.0009662788,0.000115833,0.00000190144,0.00002816817,0.3656459,0.002749864,0.6253847,0.00005976982,0.0001889092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5259619,0.00008116985,0.4709171,0.000266409,0.0001047336,0.001236471,0.0003379974,0.0003287218,0.0007654415],"genre_scores_gemma":[0.08815581,0.00007720127,0.9103583,0.00003092875,0.00007588667,0.00008414686,0.00007980819,0.00002838321,0.001109529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6964465,"threshold_uncertainty_score":0.7257292,"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."}}