{"id":"W2890657944","doi":"10.1002/sta4.215","title":"Sharpen statistical significance: Evidence thresholds and Bayes factors sharpened into Occam's razor","year":2019,"lang":"en","type":"article","venue":"Stat","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Occam's razor; occam; Null hypothesis; Statistical hypothesis testing; Idealization; Mathematics; Statistics; Prior probability; p-value; Bayes factor; Computer science; Bayes' theorem; Bayesian probability; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001085322,0.0001664998,0.0002747066,0.0001089213,0.0001677985,0.0003529806,0.0006951271,0.00007452675,0.001425033],"category_scores_gemma":[0.001540584,0.0001163653,0.00004875915,0.0003956037,0.0001966205,0.0004269395,0.0002887495,0.0001558111,0.0004018519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000360538,"about_ca_system_score_gemma":0.00007640128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002763869,"about_ca_topic_score_gemma":0.00012345,"domain_scores_codex":[0.9977675,0.00007117048,0.0004379532,0.0006757914,0.000769623,0.000277927],"domain_scores_gemma":[0.9967709,0.0020705,0.0001480057,0.0006636247,0.0001729947,0.0001740395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001912356,0.0001424853,0.5458505,0.0000883125,0.00003500264,0.00001543567,0.003652367,0.00006337618,0.01833097,0.1375011,0.1712432,0.1228861],"study_design_scores_gemma":[0.000587887,0.00074906,0.1802426,0.0002498454,0.00003734236,0.00001425336,0.001695039,0.01325515,0.007320921,0.679345,0.1154923,0.001010564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499115,0.0001711608,0.04582501,0.001219534,0.0001333377,0.0006499264,0.000172871,0.0001412318,0.001775418],"genre_scores_gemma":[0.9746517,0.00003927957,0.02310992,0.000150367,0.0000291182,0.0000423345,0.00001427714,0.00001489048,0.001948135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5418439,"threshold_uncertainty_score":0.9994878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1533180712774028,"score_gpt":0.4287373050039204,"score_spread":0.2754192337265177,"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."}}