{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5207005,0.002748707,0.01029476,0.009307638,0.00362152,0.01005717,0.007790434,0.01175373,0.007415717],"category_scores_gemma":[0.8414153,0.003394437,0.006254105,0.007918151,0.05834574,0.0353504,0.01224278,0.02641303,0.00153841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004729305,"about_ca_system_score_gemma":0.005770458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001110673,"about_ca_topic_score_gemma":0.0009754614,"domain_scores_codex":[0.4615604,0.39555,0.04181883,0.0397955,0.05774647,0.003528755],"domain_scores_gemma":[0.05588529,0.8759595,0.02236539,0.03940295,0.005260109,0.001126708],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003326626,0.0002799486,0.03504329,0.00786275,0.009252778,0.003371236,0.004406926,0.01094195,0.0009548509,0.7054634,0.01938231,0.199714],"study_design_scores_gemma":[0.0002190762,0.0003988377,0.003041774,0.0008062358,0.0006878258,0.001068018,0.0002679554,0.01906985,0.0004707075,0.9690488,0.004789995,0.0001308924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03050318,0.02547978,0.7896803,0.1330413,0.007555959,0.001251837,0.001092463,0.00120053,0.01019463],"genre_scores_gemma":[0.7663237,0.006222335,0.174046,0.03275459,0.01351769,0.002690726,0.0005299957,0.0006788755,0.003236051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4792995,"threshold_uncertainty_score":0.5910616,"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."}}