{"id":"W2803379452","doi":"10.1139/facets-2017-0121","title":"Measuring statistical evidence and multiple testing","year":2018,"lang":"en","type":"article","venue":"FACETS","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Prior probability; Statistical hypothesis testing; False positives and false negatives; False positive paradox; Measure (data warehouse); Statistical evidence; Multiple comparisons problem; Econometrics; Statistics; Computer science; Property (philosophy); Mathematics; Bayesian probability; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1687456,0.002509547,0.004525538,0.01001973,0.001969771,0.01026419,0.006339754,0.005805933,0.004212278],"category_scores_gemma":[0.5593306,0.001539041,0.003008431,0.01032509,0.0202728,0.01145141,0.00913568,0.008236705,0.0008260341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004581243,"about_ca_system_score_gemma":0.007374697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001673967,"about_ca_topic_score_gemma":0.001034095,"domain_scores_codex":[0.677485,0.255072,0.01319306,0.01697418,0.0358479,0.001427915],"domain_scores_gemma":[0.2315161,0.7033549,0.02289795,0.02743032,0.0131917,0.001609069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003422308,0.000111035,0.005971248,0.001859883,0.001207572,0.0003700925,0.001204484,0.03056059,0.0008882539,0.8028373,0.002069006,0.1525784],"study_design_scores_gemma":[0.00006972845,0.0001765598,0.001158973,0.0003906502,0.0001096512,0.0002507679,0.0001962224,0.04010614,0.000877935,0.9528206,0.003778895,0.00006387502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005266686,0.002530375,0.9844022,0.003081896,0.0001799898,0.0003040778,0.0001795668,0.0001809955,0.003874242],"genre_scores_gemma":[0.1814463,0.002112732,0.8124079,0.0009637111,0.0005697262,0.001475886,0.0002705207,0.0001131846,0.0006400358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1687456,"threshold_uncertainty_score":0.8924225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5700336014724036,"score_gpt":0.4771888699776726,"score_spread":0.09284473149473099,"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."}}