{"id":"W2100697007","doi":"10.1177/0962280214558972","title":"Events per variable (EPV) and the relative performance of different strategies for estimating the out-of-sample validity of logistic regression models","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":484,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; National Institute of Neurological Disorders and Stroke; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Statistics; Sample size determination; Logistic regression; Sample (material); Mathematics; Regression analysis; Econometrics; Mean squared error; Regression; Linear regression; Variance (accounting); Variables; Economics","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.315842,0.002793229,0.002381639,0.004318582,0.0008581803,0.003318185,0.002918366,0.002885578,0.0006402535],"category_scores_gemma":[0.5071852,0.0009556768,0.004145395,0.002087188,0.004441849,0.004880811,0.004387947,0.003861125,0.0003162101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001346676,"about_ca_system_score_gemma":0.001551827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001752906,"about_ca_topic_score_gemma":0.001441409,"domain_scores_codex":[0.803992,0.1630965,0.0092961,0.01095054,0.0110894,0.00157542],"domain_scores_gemma":[0.2198231,0.727664,0.01905683,0.0252997,0.006870094,0.001286308],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007734605,0.0005596726,0.5463855,0.001233188,0.01097742,0.0005562652,0.002639825,0.269494,0.003111103,0.007467972,0.001422545,0.1484179],"study_design_scores_gemma":[0.0005480819,0.004238619,0.2089285,0.0008154054,0.001388288,0.00100163,0.0009436856,0.7478976,0.01093504,0.02128703,0.00153448,0.0004816649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6910125,0.004195445,0.2992523,0.001228768,0.0001731707,0.0005129738,0.0006399172,0.0005106431,0.002474185],"genre_scores_gemma":[0.9456758,0.0003682784,0.05251421,0.0001982871,0.00005043752,0.0002710956,0.0005884896,0.0001147415,0.0002187386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.684158,"threshold_uncertainty_score":0.8436887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3934446952715054,"score_gpt":0.579674810655022,"score_spread":0.1862301153835166,"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."}}