{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5128993,0.001718844,0.009173487,0.005488564,0.005699564,0.01217349,0.01006538,0.07133091,0.004816257],"category_scores_gemma":[0.7461617,0.002685356,0.004210684,0.00445962,0.03944809,0.01486624,0.007871964,0.08314651,0.003721767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007921916,"about_ca_system_score_gemma":0.01276698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001662062,"about_ca_topic_score_gemma":0.002465503,"domain_scores_codex":[0.4390453,0.410695,0.07509608,0.0159456,0.05655095,0.002667061],"domain_scores_gemma":[0.08023354,0.8707775,0.01027862,0.01303709,0.02185851,0.003814793],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004600916,0.0004202009,0.003700255,0.007821221,0.00146093,0.002941218,0.003095396,0.001313079,0.001268617,0.2647825,0.5344415,0.1741543],"study_design_scores_gemma":[0.003866982,0.001000728,0.002432977,0.01079151,0.000718998,0.002767956,0.001075646,0.004559707,0.001497173,0.6045239,0.3662581,0.0005064131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0008842119,0.01028234,0.01881436,0.9344825,0.03202793,0.0004013449,0.0001972743,0.00008832444,0.002821737],"genre_scores_gemma":[0.01515093,0.004486218,0.06749894,0.8307278,0.0792328,0.001783433,0.00008451449,0.0001245627,0.0009109321],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.4871007,"threshold_uncertainty_score":0.6006819,"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."}}