{"id":"W2055948452","doi":"10.1016/j.jmpt.2006.06.009","title":"Applying Generalizability Theory to High-Stakes Objective Structured Clinical Examinations in a Naturalistic Environment","year":2006,"lang":"en","type":"article","venue":"Journal of Manipulative and Physiological Therapeutics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Generalizability theory; Cronbach's alpha; Medicine; Variance (accounting); Chiropractic; Checklist; Objective structured clinical examination; Reliability (semiconductor); Conceptualization; Licensure; Statistics; Applied psychology; Medical education; Clinical psychology; Psychology; Psychometrics; Alternative medicine; Mathematics; Computer science; Cognitive psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005422554,0.0001703288,0.0005089549,0.0001200372,0.00011495,0.0000716956,0.0003349611,0.0001184386,0.000123597],"category_scores_gemma":[0.0007161185,0.0000951406,0.0001598346,0.0002526506,0.0002268846,0.0001322791,0.00008957206,0.0003772754,0.000005790299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009652689,"about_ca_system_score_gemma":0.0000219302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001615328,"about_ca_topic_score_gemma":0.00001358997,"domain_scores_codex":[0.9955657,0.001825548,0.001253149,0.0003427151,0.0008202307,0.0001927233],"domain_scores_gemma":[0.9966997,0.002264727,0.0004874341,0.0002310653,0.0002363223,0.00008075158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002457108,0.003494824,0.4500573,0.00003202346,0.000429452,0.00005350833,0.003272166,0.08652616,0.1008552,0.1021969,0.0006308977,0.2499944],"study_design_scores_gemma":[0.0003223523,0.0003699435,0.6117197,0.000008884043,0.00001767119,0.000001638646,0.0003204623,0.00033864,0.0001829902,0.385514,0.001119478,0.00008422694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869992,0.0003077111,0.01164282,0.0003539397,0.0001958934,0.000407982,0.00000873873,0.00000392915,0.00007986461],"genre_scores_gemma":[0.9958931,0.00007273819,0.003110238,0.0006710083,0.0001922021,0.0000122472,0.000001849521,0.000004525308,0.00004210633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2833171,"threshold_uncertainty_score":0.3879721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5803482065378721,"score_gpt":0.4441747944179522,"score_spread":0.1361734121199199,"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."}}