{"id":"W4404070406","doi":"10.1186/s41512-024-00179-z","title":"The relative data hungriness of unpenalized and penalized logistic regression and ensemble-based machine learning methods: the case of calibration","year":2024,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Sunnybrook Hospital; University of Toronto; Vector Institute; Sunnybrook Health Science Centre","funders":"","keywords":"Calibration; Logistic regression; Ensemble learning; Artificial intelligence; Computer science; Machine learning; Regression; Statistics; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1391094,0.001806088,0.002723472,0.002296034,0.001300677,0.003916923,0.002399647,0.003977352,0.0009054612],"category_scores_gemma":[0.3138589,0.001296837,0.002692945,0.002048151,0.005467397,0.007447794,0.005442606,0.006538546,0.0002452383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001969459,"about_ca_system_score_gemma":0.001766195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00173955,"about_ca_topic_score_gemma":0.001212355,"domain_scores_codex":[0.9296128,0.05312405,0.003081903,0.005970933,0.007054592,0.001155819],"domain_scores_gemma":[0.5355888,0.3850818,0.0231278,0.04183191,0.0126214,0.001748345],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002093276,0.0001835485,0.05391431,0.0004399352,0.001690622,0.0003543253,0.0007081382,0.862402,0.001573568,0.0204733,0.001160111,0.05500676],"study_design_scores_gemma":[0.000190266,0.001204422,0.02329005,0.0003579753,0.0003092236,0.0004836132,0.0002712299,0.9290547,0.004680086,0.03835157,0.001592584,0.0002143317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5192547,0.007241263,0.463643,0.003918403,0.0002714457,0.0003924476,0.0005837874,0.000753327,0.003941669],"genre_scores_gemma":[0.9252821,0.0006450365,0.07184367,0.0006633418,0.0001136797,0.0002907701,0.0004427733,0.0001966488,0.0005220018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8608906,"threshold_uncertainty_score":0.7356898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4383443273239946,"score_gpt":0.5765325733102753,"score_spread":0.1381882459862807,"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."}}