{"id":"W2086773311","doi":"10.4236/ce.2013.46a005","title":"Investigating the Reliability and Validity of Self and Peer Assessment to Measure Medical Students’ Professional Competencies","year":2013,"lang":"en","type":"article","venue":"Creative Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Cronbach's alpha; Exploratory factor analysis; Self-assessment; Reliability (semiconductor); Construct validity; Interpersonal communication; Peer assessment; Medical education; Construct (python library); Applied psychology; Clinical psychology; Psychometrics; Social psychology; Medicine; Pedagogy; Computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.03971473,0.0003970696,0.0004542837,0.002467769,0.0005691157,0.001026188,0.0006864032,0.0005257632,0.0007209738],"category_scores_gemma":[0.1003124,0.0002897967,0.0007601648,0.0009071862,0.001112161,0.001304504,0.001553753,0.0006757862,0.0002773817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004979061,"about_ca_system_score_gemma":0.001016967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001268463,"about_ca_topic_score_gemma":0.002148533,"domain_scores_codex":[0.9773679,0.01150511,0.002172206,0.001271431,0.007055049,0.0006283714],"domain_scores_gemma":[0.8949536,0.06292737,0.009038904,0.005578732,0.02513592,0.002365374],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004159364,0.0005599482,0.9117493,0.0001451902,0.0003560082,0.00004787438,0.005797232,0.0005186861,0.001924289,0.0004617069,0.0003371253,0.07768662],"study_design_scores_gemma":[0.00009640139,0.002488698,0.9789878,0.0001655048,0.0001562174,0.0002782091,0.003289971,0.008569524,0.003225197,0.0006474482,0.002040858,0.00005420443],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928826,0.0003417791,0.003651604,0.00008629949,0.00006869486,0.000196765,0.00003746669,0.00001952128,0.002715355],"genre_scores_gemma":[0.9960274,0.0001136657,0.003214709,0.00002429367,0.00002920126,0.0001721007,0.00006504344,0.000007423997,0.0003462475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9602852,"threshold_uncertainty_score":0.2100341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04124359515186929,"score_gpt":0.4051475597148567,"score_spread":0.3639039645629873,"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."}}