{"id":"W4415977348","doi":"10.1016/j.bjae.2025.10.001","title":"Core concepts in statistics and research methods. Part 4: null hypothesis significance testing","year":2025,"lang":"en","type":"article","venue":"BJA Education","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Core (optical fiber); Statistical hypothesis testing; Null hypothesis; Null (SQL); p-value; Alternative hypothesis; Statistical 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09654254,0.0001115561,0.0009127383,0.0004926164,0.0001401448,0.0004568494,0.0005377249,0.00004998845,0.00125313],"category_scores_gemma":[0.1934649,0.00006737447,0.00008622569,0.002577607,0.0001003152,0.0001002149,0.00006414642,0.0001504581,0.0002259246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005947798,"about_ca_system_score_gemma":0.0005815336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001272167,"about_ca_topic_score_gemma":0.00006241505,"domain_scores_codex":[0.9849296,0.009663023,0.00301671,0.000668902,0.001518681,0.0002031388],"domain_scores_gemma":[0.9564708,0.03892009,0.001057834,0.001405734,0.002055797,0.00008977754],"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":[0.000002039379,0.000060176,0.07437672,0.00006694096,0.000016144,3.043005e-7,0.0006808032,0.00001127085,0.0004745387,0.01047765,0.1471301,0.7667033],"study_design_scores_gemma":[0.0001657097,0.00003315569,0.3956047,0.0003819008,0.0001157549,0.000002255461,0.009523733,0.01014552,0.0005136258,0.2571715,0.3261054,0.0002367],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7397811,0.01485012,0.1409337,0.0079573,0.00269147,0.004613539,0.00009156319,0.00002079472,0.08906037],"genre_scores_gemma":[0.3983558,0.0001345259,0.5504153,0.0004414786,0.0001327315,0.000429898,0.000006767265,0.00001067363,0.0500728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7664666,"threshold_uncertainty_score":0.9996598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9390683036150287,"score_gpt":0.7081336402957406,"score_spread":0.2309346633192881,"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."}}