{"id":"W3017239231","doi":"10.1016/j.jclinepi.2020.02.011","title":"The fragility of trial results involves more than statistical significance alone","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Fragility; Statistical significance; Clinical significance; Stability (learning theory); Statistical analysis; Clinical trial; Statistical power; Statistical hypothesis testing; Statistics; Medicine; Econometrics; Computer science; Mathematics; Internal medicine; Machine learning","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":["metaresearch"],"category_scores_codex":[0.131073,0.000291968,0.005850076,0.00003682973,0.00010286,0.00001281687,0.001132437,0.0006524595,0.0000894699],"category_scores_gemma":[0.971268,0.0001643557,0.001245358,0.0002433031,0.002670807,0.00006854349,0.0002201867,0.002437795,0.00001356295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002708675,"about_ca_system_score_gemma":0.0004720922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001526708,"about_ca_topic_score_gemma":0.00000610764,"domain_scores_codex":[0.9323344,0.04091737,0.02436908,0.0007279987,0.0009114893,0.0007396594],"domain_scores_gemma":[0.1508833,0.8364107,0.0104061,0.0007206054,0.0007407544,0.0008385915],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.3737523,0.001705449,0.01404268,0.0003392298,0.001235765,0.0001370354,0.000312074,0.00005776799,0.00005093983,0.4348013,0.1088325,0.06473291],"study_design_scores_gemma":[0.02610213,0.00529873,0.01694977,0.00008482905,0.0002644016,0.000008247474,0.0001063347,0.0009078471,0.0000486715,0.9450895,0.004975266,0.0001643118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1581414,0.0004941341,0.7145281,0.1172037,0.006834837,0.001393845,0.0005660502,0.00005566743,0.000782237],"genre_scores_gemma":[0.2356688,0.0007361001,0.7557409,0.003373949,0.004397907,0.000009801883,0.000001837134,0.00003337158,0.00003738575],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.840195,"threshold_uncertainty_score":0.9998636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8646482945307179,"score_gpt":0.6803537811364027,"score_spread":0.1842945133943152,"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."}}