{"id":"W2155395793","doi":"10.1177/0272989x04273142","title":"Optimal Statistical Decisions for Hospital Report Cards","year":2005,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"False positive paradox; Statistical significance; False positives and false negatives; Medicine; Statistics; Quality (philosophy); Relative value; Actuarial science; Operations management; Mathematics; Economics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002893125,0.0002522394,0.0005204086,0.0002174707,0.001303428,0.00001866209,0.0003960852,0.000614198,0.0067903],"category_scores_gemma":[0.04799006,0.0002117829,0.000156184,0.0002813821,0.0001289336,0.0001890047,0.0003072297,0.00117457,0.0008964578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000520195,"about_ca_system_score_gemma":0.001059235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000400657,"about_ca_topic_score_gemma":0.0001410499,"domain_scores_codex":[0.9938332,0.000357381,0.001915462,0.0007117187,0.002217971,0.0009642231],"domain_scores_gemma":[0.9817875,0.01576791,0.0004189416,0.0006706876,0.0005796693,0.0007753153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002399161,0.00007690751,0.09746964,0.00005733367,0.00002470192,0.0002458347,0.0007618849,0.0001877919,0.000002447618,0.005850353,0.149846,0.7452371],"study_design_scores_gemma":[0.00334924,0.0005555868,0.2548127,0.002668882,0.00005742411,0.0001514323,0.001295265,0.03583889,0.000005136088,0.009186758,0.6914039,0.0006748075],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2466143,0.0001186512,0.7414118,0.003966156,0.004400996,0.001287757,0.0001600245,0.0002055413,0.001834772],"genre_scores_gemma":[0.73979,0.00003473135,0.2555179,0.002004306,0.001642529,0.0004840121,0.00007909181,0.00005516179,0.0003922717],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7445623,"threshold_uncertainty_score":0.9999967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09029463823620998,"score_gpt":0.5133631414625724,"score_spread":0.4230685032263625,"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."}}