{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01279394,0.0005239074,0.001737465,0.0009566478,0.0005725306,0.0006086056,0.002494701,0.0002285029,0.00004572216],"category_scores_gemma":[0.1208257,0.0002359567,0.0009293253,0.002764373,0.000628782,0.0002336322,0.000487025,0.002390349,0.00001072709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001413253,"about_ca_system_score_gemma":0.0006047726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006389597,"about_ca_topic_score_gemma":0.000001175831,"domain_scores_codex":[0.9887016,0.003771411,0.003324206,0.0006889346,0.00295176,0.0005621198],"domain_scores_gemma":[0.6985071,0.2925666,0.00584312,0.001039791,0.001886879,0.0001565407],"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":[0.0008945889,0.0001251944,0.01244307,0.00002852095,0.0006021764,0.0008994265,0.01180505,0.3883353,0.00002579414,0.000002836277,0.3005793,0.2842588],"study_design_scores_gemma":[0.004120221,0.01082046,0.1306059,0.007206561,0.003333668,0.02020981,0.2107249,0.402835,0.00006225161,0.007240695,0.1990366,0.003804038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7849124,0.0003019642,0.02216568,0.1813856,0.009507583,0.001392765,0.00006249915,0.0000299524,0.0002415783],"genre_scores_gemma":[0.983302,0.00002032529,0.004835468,0.009092784,0.002622685,0.00001505093,4.697368e-7,0.00005620494,0.00005502545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2901945,"threshold_uncertainty_score":0.9999112,"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."}}