{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07076126,0.001698388,0.0030097,0.006024198,0.002322581,0.009405705,0.004247627,0.005125156,0.00354008],"category_scores_gemma":[0.359426,0.001391671,0.001847923,0.003574379,0.01754082,0.01281901,0.00642241,0.01397091,0.000682273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003773997,"about_ca_system_score_gemma":0.0029718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002642779,"about_ca_topic_score_gemma":0.001851725,"domain_scores_codex":[0.9695936,0.01777481,0.00172149,0.004461174,0.005457968,0.0009908309],"domain_scores_gemma":[0.628673,0.3308506,0.01258763,0.01365441,0.01121786,0.003016635],"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":[0.0009046578,0.00008019392,0.009369059,0.0007643555,0.0004676823,0.0003982517,0.001750901,0.01288215,0.001715604,0.7963386,0.007765001,0.1675635],"study_design_scores_gemma":[0.0001148653,0.000141036,0.002445325,0.0003403148,0.0001303096,0.0002904603,0.0002197462,0.02564638,0.001112183,0.9639342,0.005530793,0.00009430271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04918635,0.01843214,0.8711335,0.03964328,0.001766613,0.0002274587,0.0004059721,0.0006636932,0.01854098],"genre_scores_gemma":[0.6368558,0.003783991,0.3446932,0.008064496,0.003192867,0.0004973148,0.0001616084,0.0002769366,0.002473656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9292387,"threshold_uncertainty_score":0.3742258,"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."}}