{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1465839,0.001987952,0.004167129,0.008238299,0.002247982,0.01200186,0.00491396,0.005888453,0.003942574],"category_scores_gemma":[0.4383883,0.001581118,0.002010399,0.004543633,0.01949101,0.01257969,0.006221428,0.01385566,0.001171788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004097164,"about_ca_system_score_gemma":0.004308205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001651149,"about_ca_topic_score_gemma":0.0008490793,"domain_scores_codex":[0.8348597,0.125895,0.006035497,0.01483981,0.01723902,0.00113107],"domain_scores_gemma":[0.549585,0.405127,0.0142461,0.01938855,0.01010189,0.001551416],"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":[0.0001737172,0.00005476773,0.004012246,0.00068424,0.000426117,0.0003251258,0.001353464,0.01006234,0.0004737318,0.8640029,0.006201247,0.11223],"study_design_scores_gemma":[0.00004923714,0.0000377045,0.0006789028,0.0003955391,0.00005005302,0.0001668832,0.0001302216,0.02112455,0.0003695161,0.9719555,0.004987922,0.00005411397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004159541,0.002152062,0.9794192,0.007249976,0.000525929,0.0001744815,0.0001260074,0.0002436146,0.005949276],"genre_scores_gemma":[0.2493542,0.003192488,0.7354913,0.005299341,0.002751711,0.00167901,0.0002148378,0.0002753573,0.001741798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8534161,"threshold_uncertainty_score":0.7752192,"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."}}