{"id":"W4287996197","doi":"10.5281/zenodo.3566771","title":"Null hypothesis significance testing interpreted and calibrated by estimating probabilities of sign errors: A Bayes-frequentist continuum","year":2019,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Frequentist inference; Null hypothesis; Sign (mathematics); Statistical hypothesis testing; Bayes factor; Statistics; Bayes' theorem; Alternative hypothesis; Econometrics; Null (SQL); Bayesian probability; Mathematics; Computer science; Bayesian inference; Data mining; 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":[0.1698257,0.002381603,0.004619275,0.009455698,0.002416687,0.01297255,0.0058797,0.007002423,0.003854496],"category_scores_gemma":[0.4998731,0.001853482,0.002763585,0.005734655,0.02396378,0.01579249,0.00925386,0.01940642,0.00137739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004541307,"about_ca_system_score_gemma":0.004582039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001625903,"about_ca_topic_score_gemma":0.0008764543,"domain_scores_codex":[0.7938715,0.1592914,0.007005406,0.01642274,0.0221777,0.001231268],"domain_scores_gemma":[0.4837562,0.4594939,0.01692668,0.02811423,0.01021056,0.001498509],"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":[0.0001869108,0.00005897737,0.00327265,0.0007076776,0.000486171,0.0003782168,0.001670079,0.01041894,0.0005877482,0.814148,0.005464012,0.1626206],"study_design_scores_gemma":[0.00004333761,0.00004197066,0.0005417315,0.0003167935,0.00004908037,0.0001870695,0.0001073485,0.01761018,0.0004036872,0.9756238,0.005015767,0.00005919838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002529804,0.002351305,0.9840845,0.006253482,0.0004645407,0.0001202636,0.00007692086,0.0002631746,0.003855946],"genre_scores_gemma":[0.2191848,0.003339784,0.764009,0.006930096,0.002970101,0.001580395,0.0001701808,0.0003877497,0.001427934],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8301743,"threshold_uncertainty_score":0.8981349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3165564284266273,"score_gpt":0.4439534014564465,"score_spread":0.1273969730298192,"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."}}