{"id":"W1509693428","doi":"10.1111/j.1365-2923.2011.04073.x","title":"Comparison of two methods of standard setting: the performance of the three‐level Angoff method","year":2011,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tehran University of Medical Sciences and Health Services; McMaster University","keywords":"Confidence interval; Standard deviation; Normative; Test (biology); Reliability (semiconductor); Statistics; Psychology; Mathematics; Medicine; Law","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07088897,0.0009634844,0.001121359,0.005167064,0.001072077,0.001990884,0.001633675,0.001592436,0.002377878],"category_scores_gemma":[0.1811523,0.0006319739,0.001776648,0.002232304,0.001571156,0.00222939,0.003096397,0.001151938,0.0008567783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108342,"about_ca_system_score_gemma":0.002055363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001560675,"about_ca_topic_score_gemma":0.002975054,"domain_scores_codex":[0.907918,0.06298113,0.006173267,0.004728232,0.01740561,0.0007938239],"domain_scores_gemma":[0.8208171,0.1193778,0.01549156,0.01364294,0.02888422,0.001786382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007163279,0.0008860831,0.3619708,0.001647181,0.001979182,0.0001137359,0.00614126,0.002369841,0.00672019,0.008727217,0.003992242,0.598289],"study_design_scores_gemma":[0.001157199,0.008430705,0.8797864,0.001833605,0.001495575,0.001593595,0.004252448,0.04956486,0.01519914,0.01437659,0.02154694,0.0007629452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5968637,0.007131351,0.3748273,0.0006043339,0.0009342867,0.00257378,0.0005603855,0.0009444028,0.01556059],"genre_scores_gemma":[0.7106488,0.0009629778,0.2829102,0.000159672,0.0001509747,0.002478867,0.0004603074,0.0002870945,0.001941105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07088897,"threshold_uncertainty_score":0.3749012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08162076428339296,"score_gpt":0.496944829592795,"score_spread":0.415324065309402,"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."}}