{"id":"W2770322578","doi":"10.1002/bimj.201700129","title":"On the necessity and design of studies comparing statistical methods","year":2017,"lang":"en","type":"letter","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":108,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Deutsche Forschungsgemeinschaft","keywords":"Biostatistics; Library science; Epidemiology; Medical statistics; Medicine; Computer science; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02113937,0.0004523844,0.002383266,0.000736805,0.0005127874,0.0002739558,0.001121338,0.0007650533,0.0001798209],"category_scores_gemma":[0.5858209,0.0002447036,0.000259154,0.0005681716,0.001520291,0.00005126548,0.0004639932,0.004273807,0.00001029415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001275732,"about_ca_system_score_gemma":0.0001132027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002832928,"about_ca_topic_score_gemma":5.189801e-8,"domain_scores_codex":[0.9863763,0.009569925,0.001774451,0.000487348,0.001253938,0.0005379871],"domain_scores_gemma":[0.5686854,0.4284523,0.00166648,0.000652361,0.0003744248,0.0001690607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001324484,0.00011048,0.00003564299,0.0004016868,0.0008890102,0.0003763396,0.00003689432,4.08391e-7,0.00002168912,0.01948901,0.9420556,0.03645077],"study_design_scores_gemma":[0.0005972907,0.0005156116,0.0002091708,0.0005469901,0.0005881491,0.000133327,0.0000193593,0.0002313668,0.0001220663,0.98863,0.008109242,0.0002974145],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005083825,0.001036926,0.909142,0.08756159,0.001439946,0.0003998107,0.00007169287,0.00002121801,0.0002760396],"genre_scores_gemma":[0.0003464722,0.000483768,0.9741894,0.02233281,0.002440681,0.00001332857,7.79843e-7,0.00005576722,0.000136969],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.969141,"threshold_uncertainty_score":0.9980234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9022525894811605,"score_gpt":0.6758531036730725,"score_spread":0.226399485808088,"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."}}