{"id":"W2925846695","doi":"10.1136/bmjebm-2019-111174","title":"Assessing assumptions for statistical analyses in randomised clinical trials","year":2019,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"Novo Nordisk Fonden","keywords":"Statistical power; Statistical hypothesis testing; Clinical trial; Statistical analysis; Computer science; Statistical model; Econometrics; Medical physics; Management science; Data science; Medicine; Statistics; Machine learning; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6514105,0.000372738,0.01069666,0.0009201188,0.000097782,0.0005706621,0.001273046,0.0001854335,0.03049665],"category_scores_gemma":[0.8360813,0.0001593237,0.00260415,0.001690995,0.0002273395,0.0005737398,0.0000488186,0.000302672,0.001267043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006789946,"about_ca_system_score_gemma":0.0006219662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005494031,"about_ca_topic_score_gemma":0.00004675775,"domain_scores_codex":[0.8520341,0.09455587,0.04235888,0.002064406,0.008381313,0.0006054457],"domain_scores_gemma":[0.4141476,0.5654708,0.01300244,0.004657028,0.002177734,0.0005444282],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002134494,0.0002735889,0.1237971,0.0004479366,0.0005174236,0.00003309165,0.0001070023,0.00130782,0.001396618,0.00159627,0.7974027,0.07098584],"study_design_scores_gemma":[0.08785263,0.001768971,0.3532095,0.0095987,0.007833742,0.0000219783,0.003672826,0.339555,0.000139127,0.02301883,0.1719331,0.001395552],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07567447,0.003354019,0.8854598,0.02059638,0.001981914,0.0117344,0.000338734,0.00001682122,0.0008434198],"genre_scores_gemma":[0.9425531,0.0001409314,0.04856948,0.003853515,0.001492465,0.0009222199,0.0003969778,0.00002918197,0.002042103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8668786,"threshold_uncertainty_score":0.9995106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9827549661353883,"score_gpt":0.784218247525338,"score_spread":0.1985367186100503,"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."}}