{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03290375,0.000177432,0.0008481187,0.00009037222,0.0001726553,0.00001930212,0.0005253757,0.000176754,0.0002047556],"category_scores_gemma":[0.2396518,0.00008294976,0.00006006138,0.0002394961,0.002994153,0.00007345768,0.0003285731,0.000897509,2.885302e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000322099,"about_ca_system_score_gemma":0.0002409571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001186971,"about_ca_topic_score_gemma":0.000009171365,"domain_scores_codex":[0.9878017,0.0088264,0.001088635,0.0003376075,0.001465856,0.0004797842],"domain_scores_gemma":[0.7031545,0.2955875,0.0002611755,0.0004110624,0.0004396992,0.0001460556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003435344,0.0001197633,0.0001946041,0.00114782,0.00002272686,3.494843e-7,0.0006867333,0.00001395549,0.00006043642,0.8486877,0.00003172585,0.1486906],"study_design_scores_gemma":[0.0005507544,0.0002831066,0.0003452689,0.0004619404,0.00002867048,5.841314e-7,0.0001652232,0.4218926,0.0001462419,0.576071,0.000004828064,0.00004983165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003192432,0.00003326925,0.9945339,0.0002634128,0.00013959,0.0006872028,0.0001167371,0.000006094737,0.001027356],"genre_scores_gemma":[0.2263138,0.00003373444,0.7734734,0.00001004326,0.00003644657,0.0001068403,0.000002983891,0.00001315596,0.000009568374],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4218786,"threshold_uncertainty_score":0.9997191,"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."}}