{"id":"W2803912231","doi":"10.1080/00031305.2018.1475304","title":"Two-Tailed <i>p</i> -Values and Coherent Measures of Evidence","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Null hypothesis; p-value; Null (SQL); Statistical hypothesis testing; Interpretation (philosophy); Alternative hypothesis; Econometrics; Mathematics; Value (mathematics); Statistics; Set (abstract data type); Measure (data warehouse); Statistical evidence; Statistical significance; Mathematical economics; Computer science; Data mining; Linguistics; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.0006533041,0.000146559,0.0004040087,0.00003025242,0.0001302796,0.00001633229,0.0001878982,0.00001126754,0.0000360595],"category_scores_gemma":[0.003228705,0.00008368707,0.0000286201,0.0001643843,0.001914845,0.00004918238,0.00007857529,0.00009721339,0.00000655214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001764888,"about_ca_system_score_gemma":0.00003382205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002196051,"about_ca_topic_score_gemma":0.00009157609,"domain_scores_codex":[0.9985713,0.000362592,0.000313248,0.0002179206,0.0002933331,0.0002415992],"domain_scores_gemma":[0.9947106,0.004327714,0.0003337478,0.0003500772,0.0001899736,0.00008789181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002949295,0.00007185863,0.0005944262,0.00007849379,0.00008465396,0.000006455753,0.002113816,0.000003473133,0.005175688,0.4341122,0.001935048,0.5555289],"study_design_scores_gemma":[0.0002208635,0.0006447245,0.002088167,0.0001353976,0.0001305287,0.000006529671,0.0008823166,0.001411824,0.001532514,0.9924193,0.000349123,0.0001787234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04431131,0.0001403248,0.9537832,0.0002237489,0.00006004407,0.0002366212,0.00008892934,0.00003557203,0.001120294],"genre_scores_gemma":[0.515821,0.00006785402,0.483686,0.0002199844,0.00007123846,0.00001328382,4.302085e-7,0.0000163591,0.0001038721],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5583071,"threshold_uncertainty_score":0.7055326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3190207158526712,"score_gpt":0.4897757391841812,"score_spread":0.17075502333151,"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."}}