{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003768862,0.00009467117,0.0001533512,0.00001856719,0.0001236351,0.00002435578,0.00006222753,0.00003474017,0.00003869453],"category_scores_gemma":[0.02372618,0.00008073234,0.000009100401,0.00005770176,0.0001384701,0.00009423231,0.00007307831,0.00009331654,0.0000235918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001609343,"about_ca_system_score_gemma":0.00001496039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001291554,"about_ca_topic_score_gemma":0.00001139211,"domain_scores_codex":[0.9991683,0.00007059042,0.0001675612,0.0002220252,0.0001519313,0.0002195676],"domain_scores_gemma":[0.9946601,0.004930158,0.0000430806,0.0001480557,0.0001081278,0.0001105077],"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":[0.0001063174,0.0001719163,0.01378042,0.0005619911,0.00004690091,0.00005495061,0.001811652,0.00002199114,0.04499331,0.514245,0.001898982,0.4223066],"study_design_scores_gemma":[0.0003259339,0.0001793289,0.006424411,0.000308578,0.0000289686,0.00002332315,0.00005647788,0.04552393,0.0040115,0.9423828,0.0004860639,0.0002486723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06275062,0.00005853508,0.9358121,0.00004394438,0.00006654353,0.0001231615,0.00001855822,0.00006926213,0.001057337],"genre_scores_gemma":[0.4770325,0.000002003326,0.5228239,0.00002472715,0.00004860708,0.000002940069,1.89102e-7,0.000008588356,0.00005656789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4281379,"threshold_uncertainty_score":0.9844974,"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."}}