{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2583565,0.002202298,0.00579115,0.01526275,0.002549556,0.01248225,0.007863407,0.01253512,0.007698921],"category_scores_gemma":[0.674191,0.001693594,0.004077542,0.01825173,0.0354148,0.01589793,0.008314194,0.01518216,0.002509891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002621683,"about_ca_system_score_gemma":0.00487502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003963722,"about_ca_topic_score_gemma":0.0003994108,"domain_scores_codex":[0.6655838,0.2310072,0.03745366,0.02507816,0.03891453,0.001962591],"domain_scores_gemma":[0.1733864,0.7268989,0.03921935,0.04209789,0.01564096,0.00275656],"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":[0.001328319,0.0001987469,0.01168363,0.00918882,0.003524476,0.001892939,0.003073117,0.005284357,0.001725899,0.7947015,0.03115004,0.1362482],"study_design_scores_gemma":[0.0001786583,0.0004438273,0.002384517,0.001805223,0.0004497954,0.0009923122,0.0006272022,0.004410388,0.001215326,0.9621766,0.02514497,0.0001712462],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01031167,0.01643298,0.9226426,0.02554382,0.004902898,0.001142081,0.002565154,0.0008844018,0.01557432],"genre_scores_gemma":[0.2609469,0.006381085,0.6985741,0.01432601,0.006170082,0.009219023,0.001619848,0.0005764203,0.002186534],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7416435,"threshold_uncertainty_score":0.9145785,"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."}}