{"id":"W2885084523","doi":"10.1097/phm.0000000000001016","title":"A Tale of Confusion From Overlapping Confidence Intervals","year":2018,"lang":"en","type":"letter","venue":"American Journal of Physical Medicine & Rehabilitation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Confusion; Medicine; Significant difference; Randomized controlled trial; Treatment effect; Statistics; Internal medicine; Mathematics; Psychology","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","sts"],"consensus_categories":[],"category_scores_codex":[0.003493292,0.0004187748,0.003344745,0.0002923525,0.00003814194,0.00001371836,0.0005958203,0.0002520798,0.0003950915],"category_scores_gemma":[0.2188181,0.0002976795,0.0006637163,0.0004567377,0.004123206,0.0001296397,0.0001022407,0.001803852,0.00001331826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371955,"about_ca_system_score_gemma":0.0001754679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001970046,"about_ca_topic_score_gemma":0.000001478399,"domain_scores_codex":[0.9917694,0.0027477,0.002980576,0.0004566215,0.001727258,0.0003184493],"domain_scores_gemma":[0.8037402,0.1891463,0.004975132,0.0005453738,0.001452204,0.0001408322],"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":[0.0008216182,0.0006620057,0.0001405808,0.001391326,0.0009231301,0.0001089352,0.01066897,0.000002244337,0.008828848,0.006725983,0.4846671,0.4850593],"study_design_scores_gemma":[0.001316349,0.05744739,0.0004315563,0.008166345,0.0009043973,0.00001160602,0.001399019,0.0001354832,0.0001747861,0.9166107,0.01307822,0.0003242097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.3734733,0.0002040851,0.1604184,0.4583321,0.004531047,0.001689618,0.0003633798,0.00008160599,0.0009063901],"genre_scores_gemma":[0.1706161,0.00001275972,0.7236653,0.07201081,0.03339698,0.00002769589,0.00002022525,0.0001684753,0.00008167864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9098846,"threshold_uncertainty_score":0.9999475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1750678527568298,"score_gpt":0.5043287647513413,"score_spread":0.3292609119945114,"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."}}