{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07428406,0.001696708,0.002473397,0.002671639,0.0009774631,0.005164082,0.003158463,0.001991373,0.004692643],"category_scores_gemma":[0.2368434,0.00173364,0.000952077,0.002352874,0.003181059,0.005027402,0.002767955,0.003203273,0.0005703475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00633328,"about_ca_system_score_gemma":0.007046926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001712349,"about_ca_topic_score_gemma":0.001264411,"domain_scores_codex":[0.9081697,0.07839581,0.002408917,0.003045743,0.006084035,0.001895845],"domain_scores_gemma":[0.6596159,0.3046205,0.01464342,0.008596119,0.01038614,0.002138006],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002955916,0.0006360101,0.009416929,0.0005406759,0.0002398084,0.0002018868,0.0004549514,0.671203,0.0007638344,0.1774188,0.004479117,0.1316892],"study_design_scores_gemma":[0.0005983727,0.0007767844,0.002188783,0.0001486901,0.00008045889,0.0001064863,0.0002337004,0.8658645,0.001536643,0.1258311,0.002548272,0.00008635454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09194056,0.0006073514,0.895922,0.002915394,0.0001234139,0.002253101,0.0003806088,0.000554843,0.005302687],"genre_scores_gemma":[0.5606315,0.000320499,0.4352816,0.0005317368,0.0001070182,0.001411562,0.0005023625,0.00008398739,0.001129807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9257159,"threshold_uncertainty_score":0.3928564,"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."}}