{"id":"W2994409524","doi":"10.1080/00031305.2020.1816214","title":"Null Hypothesis Significance Testing Interpreted and Calibrated by Estimating Probabilities of Sign Errors: A Bayes-Frequentist Continuum","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bayes factor; Frequentist inference; Posterior probability; Bayesian probability; Statistics; Bayes' theorem; Mathematics; p-value; Statistical hypothesis testing; Sign (mathematics); Null hypothesis; Prior probability; Alternative hypothesis; Statistical power; Econometrics; Bayesian inference; Mathematical analysis","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001482716,0.0003422981,0.001252717,0.0000377161,0.0001402364,0.00008238522,0.0004764592,0.00005224674,0.00009949881],"category_scores_gemma":[0.2038962,0.0002600042,0.00007684228,0.0006448548,0.002303437,0.00007323117,0.0001581667,0.0003551701,0.000007222949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003968157,"about_ca_system_score_gemma":0.00009418105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005778697,"about_ca_topic_score_gemma":0.0000247433,"domain_scores_codex":[0.9955253,0.00171395,0.001362503,0.0005524341,0.0003943502,0.0004514423],"domain_scores_gemma":[0.8925856,0.1051249,0.001406964,0.0004294578,0.0002136232,0.000239461],"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":[0.002390892,0.0007315489,0.008218993,0.003684911,0.001319089,0.000130817,0.01375035,0.00007439631,0.1036711,0.07198223,0.05973429,0.7343113],"study_design_scores_gemma":[0.001055002,0.001891505,0.002400536,0.000559864,0.0005195353,0.00001135761,0.002924074,0.05728111,0.005282698,0.9271859,0.00009929095,0.0007891363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1011124,0.00004973148,0.8932944,0.001440707,0.0001261186,0.001129726,0.00174927,0.0002456828,0.0008519814],"genre_scores_gemma":[0.3673545,0.000002462898,0.6318411,0.000588876,0.00008349469,0.00005224842,0.000002143413,0.00005214943,0.00002310593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8552037,"threshold_uncertainty_score":0.9999852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3681754553938135,"score_gpt":0.4518311482418546,"score_spread":0.08365569284804114,"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."}}