{"id":"W2782320564","doi":"10.1007/s40037-017-0391-8","title":"Detecting rater bias using a person-fit statistic: a Monte Carlo simulation study","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Monte Carlo method; Statistic; Medical physics; Computer science; Psychology; Medicine; Statistics; Mathematics","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":["metaresearch"],"category_scores_codex":[0.2806951,0.00103364,0.001291325,0.001736263,0.0008644286,0.003138626,0.002323083,0.002259816,0.005541095],"category_scores_gemma":[0.6722556,0.0006966166,0.002719156,0.00185799,0.004433083,0.003061492,0.001920113,0.002034745,0.0008956212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581014,"about_ca_system_score_gemma":0.003827197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003711669,"about_ca_topic_score_gemma":0.002537939,"domain_scores_codex":[0.5676581,0.4047977,0.007938519,0.005587132,0.01295982,0.001058587],"domain_scores_gemma":[0.1575713,0.7989922,0.01842883,0.01719938,0.007265722,0.0005426266],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002689688,0.001266844,0.5564399,0.002524085,0.006339688,0.0007234232,0.0129611,0.06347778,0.001941688,0.1100054,0.008393941,0.2332364],"study_design_scores_gemma":[0.001120971,0.006674409,0.2180707,0.003730731,0.001901422,0.002115943,0.00458849,0.5677719,0.01118781,0.1609193,0.02137703,0.0005413541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2065622,0.0009102115,0.7746817,0.003159989,0.0002378803,0.002958302,0.0004523496,0.000631272,0.01040602],"genre_scores_gemma":[0.8000673,0.0001970581,0.1950971,0.0008166824,0.0001001219,0.002991987,0.0001299482,0.00009942762,0.0005004747],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7193049,"threshold_uncertainty_score":0.887031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4676450050714238,"score_gpt":0.5170803826767165,"score_spread":0.04943537760529271,"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."}}