{"id":"W2587882333","doi":"10.1016/j.pmrj.2017.02.003","title":"Demonstrating Construct Validity of the American Board of Physical Medicine and Rehabilitation Part I Examination: An Analysis of Dimensionality","year":2017,"lang":"en","type":"article","venue":"PM&R","topic":"Medical Education and Admissions","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. John's Rehab Hospital; Toronto Rehabilitation Institute; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Construct validity; United States Medical Licensing Examination; Item response theory; Rasch model; Construct (python library); Psychometrics; Certification; Empirical examination; Dimension (graph theory); Local independence; Psychology; Medicine; Clinical psychology; Computer science; Mathematics; Medical education; Developmental psychology; Actuarial 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005003577,0.00005665394,0.000407646,0.00006527449,0.00008936198,0.000002097169,0.00007574913,0.00001959431,0.0001506788],"category_scores_gemma":[0.01110611,0.00003401185,0.00008794565,0.0001988249,0.001761334,0.00004171705,0.00002831031,0.00007295141,9.278873e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009196149,"about_ca_system_score_gemma":0.0001438608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002402911,"about_ca_topic_score_gemma":0.00002280556,"domain_scores_codex":[0.9990235,0.000162338,0.0003003993,0.0001272038,0.0003303501,0.00005618219],"domain_scores_gemma":[0.9978815,0.0007201142,0.0005569166,0.0004296062,0.0002303549,0.0001814469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003044558,0.0003482676,0.9585882,0.0001331379,0.0001536932,2.619958e-7,0.00241442,0.000004018157,0.01565132,0.003793344,0.0001964056,0.01868652],"study_design_scores_gemma":[0.0002834665,0.0003434479,0.9922568,0.000155519,0.0006072957,0.00000107963,0.001707606,0.002540331,0.001728036,0.0002641985,0.00008313743,0.00002906345],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940131,0.000008565159,0.0000309397,0.005011499,0.00005184386,0.0001038404,0.00001091468,0.000003746498,0.0007655422],"genre_scores_gemma":[0.9988799,0.00000423927,0.0009003474,0.0001144082,0.00005604785,0.000002480079,0.000009758749,0.000002429005,0.00003036572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03366866,"threshold_uncertainty_score":0.9972237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06692627245188452,"score_gpt":0.4056461410547016,"score_spread":0.3387198686028171,"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."}}