{"id":"W3190043208","doi":"10.1037/met0000678","title":"Why multiple hypothesis test corrections provide poor control of false positives in the real world.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Prioris.ai (Canada)","funders":"","keywords":"False positive paradox; Statistical hypothesis testing; False positives and false negatives; Statistics; Test (biology); Econometrics; Psychology; Multiple comparisons problem; Statistical analysis; Control (management); Mathematics; Artificial intelligence; Computer science","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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1166763,0.0002365186,0.002046082,0.0004958214,0.00008712797,0.0004790074,0.001424419,0.00009639463,0.002932782],"category_scores_gemma":[0.1071601,0.00008530804,0.001328415,0.003258397,0.0001711574,0.0001222712,0.00004561371,0.0003102534,0.0003749368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001939804,"about_ca_system_score_gemma":0.00001415975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000600009,"about_ca_topic_score_gemma":0.0001342262,"domain_scores_codex":[0.9601363,0.03277498,0.004380398,0.0009298499,0.001532741,0.0002457188],"domain_scores_gemma":[0.8672994,0.1295035,0.001021876,0.001802057,0.0002837277,0.00008942338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006612442,0.0009042349,0.08489706,0.00005729333,0.0002487803,0.00004034522,0.00148385,0.00005471962,0.009905372,0.005719324,0.05171995,0.8449029],"study_design_scores_gemma":[0.0006729485,0.000502963,0.5773417,0.0001653089,0.0005784538,0.00004209107,0.002658999,0.02276428,0.0003964746,0.07956842,0.3148707,0.0004376976],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07371745,0.003544851,0.8293207,0.01535756,0.001516385,0.00290142,0.0001108043,0.00005000308,0.07348089],"genre_scores_gemma":[0.8504677,0.00003483228,0.1447814,0.002028402,0.00008671563,0.0002103555,8.212561e-7,0.000008817813,0.002380968],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8444653,"threshold_uncertainty_score":0.9979787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7374936027261868,"score_gpt":0.6119179092144343,"score_spread":0.1255756935117525,"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."}}