{"id":"W2262777419","doi":"10.3352/jeehp.2016.13.6","title":"Calibrating the Medical Council of Canada’s Qualifying Examination Part I using an integrated item response theory framework: a comparison of models and designs","year":2016,"lang":"en","type":"article","venue":"Journal of Educational Evaluation for Health Professions","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Polytomous Rasch model; Item response theory; Calibration; Statistics; Set (abstract data type); Test (biology); Computer science; Type I and type II errors; Econometrics; Multiple choice; Psychology; Mathematics; Significant difference; Psychometrics; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1180381,0.001765864,0.001388992,0.004175979,0.001199052,0.003445667,0.003131078,0.001702539,0.001847751],"category_scores_gemma":[0.217585,0.001029333,0.003199374,0.003384627,0.002230919,0.00171443,0.003364719,0.002207275,0.0005405065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01408981,"about_ca_system_score_gemma":0.01874368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1437404,"about_ca_topic_score_gemma":0.1059741,"domain_scores_codex":[0.9073586,0.06981567,0.002331187,0.005861464,0.01327068,0.001362443],"domain_scores_gemma":[0.8410727,0.1187523,0.01074425,0.009187324,0.01903572,0.001207638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002079107,0.001305306,0.5156476,0.001360341,0.002693549,0.00008813637,0.007503178,0.1118068,0.001329825,0.01067055,0.003489974,0.3420256],"study_design_scores_gemma":[0.001009952,0.003161336,0.4068872,0.001175525,0.001116718,0.0001702272,0.003890522,0.5623159,0.003354809,0.01099253,0.005392258,0.0005331532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7065201,0.001351498,0.2783851,0.00104008,0.0001142941,0.005459342,0.0006991333,0.0009946662,0.005435816],"genre_scores_gemma":[0.8078219,0.0004204489,0.1866233,0.0003295757,0.00003085259,0.002552681,0.001127204,0.0001170558,0.0009769341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1437404,"threshold_uncertainty_score":0.6242524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8970046108208954,"score_gpt":0.6521780930522075,"score_spread":0.2448265177686879,"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."}}