{"id":"W3198867954","doi":"10.15626/mp.2020.2506","title":"What to make of equivalence testing with a post-specified margin?","year":2021,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Margin (machine learning); Equivalence (formal languages); Frequentist inference; Post hoc; Statistical hypothesis testing; Computer science; Econometrics; Mathematics; Statistics; Machine learning; Artificial intelligence; Bayesian probability; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003040569,0.0002581723,0.001420514,0.00009937153,0.00004216823,0.00004431875,0.0004210755,0.0001825769,0.00222439],"category_scores_gemma":[0.08739571,0.0001902313,0.0002050503,0.0007113859,0.0002178189,0.00006997745,0.0001964437,0.0003223,0.0001008042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001453027,"about_ca_system_score_gemma":0.00006747173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003647338,"about_ca_topic_score_gemma":0.00001671734,"domain_scores_codex":[0.9959667,0.001346258,0.001095718,0.000740532,0.0004071979,0.0004435752],"domain_scores_gemma":[0.962277,0.03530516,0.0003559842,0.001203404,0.0006723671,0.0001860901],"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":[0.003851331,0.003917559,0.002380487,0.00119419,0.007436152,0.002372291,0.001574214,0.00001956944,0.09283659,0.3302986,0.01271499,0.5414041],"study_design_scores_gemma":[0.002188158,0.001571376,0.01187005,0.0002496763,0.002215721,0.0002587711,0.0002684219,0.00001415352,0.008924169,0.963473,0.008414783,0.0005516959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09944557,0.001388737,0.8428853,0.02166892,0.004187721,0.001649632,0.0002247349,0.0002600442,0.02828941],"genre_scores_gemma":[0.01248875,0.0000508535,0.9814989,0.004756562,0.0001658217,0.00008772543,0.000001480232,0.00004990491,0.0009000191],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6331744,"threshold_uncertainty_score":0.9986877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8258386333211938,"score_gpt":0.6156700248907838,"score_spread":0.21016860843041,"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."}}