{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5300969,0.002364435,0.01044474,0.005813953,0.00351006,0.01474725,0.0125597,0.01688892,0.003794413],"category_scores_gemma":[0.8292308,0.002035492,0.00697221,0.006589803,0.03624928,0.03028084,0.00578765,0.0224741,0.001749168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006537911,"about_ca_system_score_gemma":0.009961091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00169631,"about_ca_topic_score_gemma":0.001548796,"domain_scores_codex":[0.4068259,0.4946236,0.05199464,0.01354641,0.031726,0.001283389],"domain_scores_gemma":[0.1915103,0.7323112,0.02780389,0.02907832,0.01782705,0.001469183],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003035622,0.0002192868,0.003199628,0.03848174,0.006082676,0.0008362329,0.006517854,0.003519087,0.001010382,0.5411707,0.06158977,0.3343372],"study_design_scores_gemma":[0.001113232,0.000586189,0.001340741,0.01991832,0.001407425,0.0005864396,0.001424791,0.004558206,0.001238344,0.9129342,0.05465475,0.0002373945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.00411331,0.1089834,0.397398,0.4456781,0.03100897,0.002784909,0.000607067,0.0005545775,0.008871814],"genre_scores_gemma":[0.1408626,0.03154605,0.6381667,0.1421812,0.03314096,0.0119026,0.0003466617,0.0004610755,0.001392164],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4699031,"threshold_uncertainty_score":0.5794742,"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."}}