{"id":"W3113194203","doi":"10.1016/j.bjps.2020.12.029","title":"Optimising the computerised adaptive test to reliably reduce the burden of administering the CLEFT-Q: A Monte Carlo simulation study","year":2020,"lang":"en","type":"letter","venue":"Journal of Plastic Reconstructive & Aesthetic Surgery","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto; McMaster University","funders":"Canadian Institutes of Health Research; National Institute for Health and Care Research","keywords":"Monte Carlo method; Test (biology); Computer science; Computerized adaptive testing; Reliability engineering; Statistics; Engineering; Mathematics; Psychometrics","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":[],"consensus_categories":[],"category_scores_codex":[0.01145042,0.0004080766,0.0005142623,0.0004642048,0.0002733722,0.001163184,0.001536723,0.002122547,0.00310563],"category_scores_gemma":[0.09188307,0.0004708358,0.0004930834,0.0005331704,0.0007929142,0.001005864,0.0007194487,0.002165369,0.0005428298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001072537,"about_ca_system_score_gemma":0.002286769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008807807,"about_ca_topic_score_gemma":0.006714948,"domain_scores_codex":[0.9956905,0.003385852,0.0001693923,0.0001857985,0.0004372222,0.0001311866],"domain_scores_gemma":[0.9248683,0.07016435,0.0008412905,0.001990683,0.001825358,0.0003099698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008759355,0.002161721,0.0609722,0.0002471977,0.0002602069,0.001037437,0.0006866542,0.5702035,0.005636906,0.01562027,0.005360229,0.3290543],"study_design_scores_gemma":[0.0006735314,0.0008974742,0.005617124,0.00003686869,0.00005218549,0.0005027878,0.00006867232,0.9823096,0.00229418,0.00611734,0.001383395,0.00004668687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5382662,0.0003763057,0.4466089,0.00635774,0.0002028984,0.0009036489,0.0002776754,0.00079828,0.006208378],"genre_scores_gemma":[0.7892513,0.00009913457,0.2082959,0.000938944,0.00003031127,0.0003548226,0.00007483005,0.00008998166,0.0008647533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01145042,"threshold_uncertainty_score":0.06055635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3333822597090917,"score_gpt":0.3995747554086898,"score_spread":0.06619249569959812,"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."}}