{"id":"W3096180835","doi":"","title":"Testing with p*-values: Between p-values and e-values","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Frequentist inference; Statistics; Value (mathematics); Bayesian probability; Expected value; Combinatorics; Bayesian inference","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":[],"category_scores_codex":[0.09449643,0.002592736,0.003842498,0.006352849,0.001801898,0.009294457,0.005357601,0.005644927,0.009095591],"category_scores_gemma":[0.4720333,0.00108174,0.00296165,0.008310574,0.02141539,0.01592727,0.006936415,0.012351,0.002007279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002422241,"about_ca_system_score_gemma":0.003553802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007523294,"about_ca_topic_score_gemma":0.0004221039,"domain_scores_codex":[0.8461635,0.1105276,0.006678461,0.01884037,0.01649487,0.001295203],"domain_scores_gemma":[0.3317111,0.6201132,0.01726431,0.02319177,0.006137545,0.001582135],"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":[0.001543351,0.0003152453,0.03298915,0.00336844,0.003091715,0.001850803,0.001886492,0.01992011,0.001945468,0.7096552,0.01376417,0.2096698],"study_design_scores_gemma":[0.0001552924,0.0004256407,0.003901487,0.0005500588,0.0002274587,0.0007819083,0.0003416038,0.02428905,0.001505307,0.9544991,0.0132047,0.0001182969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01765154,0.005359236,0.9582005,0.006031994,0.00114805,0.000406614,0.001154411,0.0008193866,0.009228365],"genre_scores_gemma":[0.4671177,0.002706455,0.5135961,0.005840252,0.002312928,0.004082329,0.00141651,0.0007765254,0.002151265],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9055036,"threshold_uncertainty_score":0.4997509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6909092857363631,"score_gpt":0.4098744284431825,"score_spread":0.2810348572931806,"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."}}