{"id":"W1987762341","doi":"10.1177/0959354307086923","title":"Why <i>P</i> Values Are Not a Useful Measure of Evidence in Statistical Significance Testing","year":2008,"lang":"en","type":"article","venue":"Theory & Psychology","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"p-value; Replication (statistics); Null hypothesis; Statistical hypothesis testing; Value (mathematics); Psychology; Measure (data warehouse); Social psychology; Statistics; Epistemology; Cognitive psychology; Econometrics; Computer science; Mathematics; Philosophy; Data mining","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004532648,0.0001309902,0.0003517844,0.0001862123,0.0001056311,0.0000149756,0.0008629939,0.00008366386,0.0001929319],"category_scores_gemma":[0.01243438,0.0000943901,0.00005042208,0.001007606,0.0008093516,0.000112471,0.00008376577,0.0002395726,0.00007885764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001779691,"about_ca_system_score_gemma":0.00005445624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005042283,"about_ca_topic_score_gemma":0.00002566769,"domain_scores_codex":[0.9972171,0.0006992743,0.0007067904,0.0005631787,0.0005438179,0.0002698373],"domain_scores_gemma":[0.9909208,0.00750311,0.0003605297,0.0008115803,0.0003345143,0.0000693957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001653453,0.001336962,0.3965958,0.0000464714,0.00003453131,0.0002431234,0.003389944,0.0004139434,0.06799056,0.1812937,0.1872839,0.1597175],"study_design_scores_gemma":[0.0002768611,0.000246619,0.2367709,0.0001702418,0.000009356835,0.0001329513,0.0001536381,0.0004367701,0.00201825,0.7564407,0.003122121,0.0002215169],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6910092,0.0002830172,0.2969346,0.003612075,0.0001723073,0.0005096528,0.00006298172,0.0001739849,0.007242178],"genre_scores_gemma":[0.969535,0.00001941175,0.02823452,0.001958638,0.00003891086,0.00005107921,6.989858e-7,0.00001230777,0.0001494212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.575147,"threshold_uncertainty_score":0.9958843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6032423430011634,"score_gpt":0.4851480948478012,"score_spread":0.1180942481533622,"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."}}