{"id":"W2099457688","doi":"10.1111/bmsp.12015","title":"Evaluating clinical significance: Incorporating robust statistics with normative comparison tests","year":2013,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Statistics; Normative; Econometrics; Statistical hypothesis testing; Mathematics; Epistemology; Philosophy","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","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008745326,0.0004092379,0.002289513,0.0001127979,0.0002225252,0.0002669047,0.0004571406,0.0003574651,0.001810756],"category_scores_gemma":[0.115373,0.0003286546,0.0001394296,0.0002688788,0.001882453,0.0002555984,0.000133113,0.001767227,0.00009774339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004262259,"about_ca_system_score_gemma":0.0001590453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001404856,"about_ca_topic_score_gemma":0.00001054344,"domain_scores_codex":[0.989989,0.002990463,0.004742363,0.0005806143,0.001051345,0.0006461556],"domain_scores_gemma":[0.9140266,0.0816954,0.00199552,0.0003289632,0.001201414,0.0007521299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006887756,0.003091198,0.003508532,0.0008614534,0.0005616484,0.0009975286,0.000276813,0.00002304709,0.0001118841,0.4520267,0.0418581,0.4959943],"study_design_scores_gemma":[0.003100289,0.003383483,0.01303599,0.0006428364,0.0003226431,0.002351528,0.0002469734,0.007094473,0.00000884751,0.9693679,0.00003572528,0.0004093139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04905751,0.0001173288,0.9475271,0.0004721711,0.0003462035,0.0007619636,0.0002091629,0.00004345259,0.001465145],"genre_scores_gemma":[0.09328864,0.00006195567,0.9056772,0.0004542693,0.0003506414,0.00004128045,0.000004271246,0.0000618045,0.00005994684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5173412,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6101012297971987,"score_gpt":0.6102618176534461,"score_spread":0.0001605878562473961,"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."}}