{"id":"W2292070591","doi":"10.1371/journal.pone.0150563","title":"The Accuracy of Computerized Adaptive Testing in Heterogeneous Populations: A Mixture Item-Response Theory Analysis","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Arthritis Research Centre of Canada; University of British Columbia; Western University; Trinity Western University; Providence Health Care Research Institute; Providence Health Care","funders":"Canadian Arthritis Network; Canada Research Chairs; Trinity Western University","keywords":"Latent class model; Statistics; Latent variable; Item response theory; Computerized adaptive testing; Population; Categorical variable; Polytomous Rasch model; Sample (material); Sample size determination; Latent variable model; Referent; Mathematics; Psychology; Medicine; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.1382416,0.001133524,0.001735376,0.003668054,0.0005572352,0.00284959,0.003066446,0.001788615,0.001936069],"category_scores_gemma":[0.3729629,0.0008358784,0.003210219,0.002952866,0.00321249,0.002745013,0.003319264,0.001955451,0.0002953229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002913576,"about_ca_system_score_gemma":0.001597147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003851289,"about_ca_topic_score_gemma":0.002430981,"domain_scores_codex":[0.8866906,0.09575307,0.003883773,0.006934147,0.006126417,0.0006120431],"domain_scores_gemma":[0.533935,0.4192129,0.0164382,0.02264543,0.006960487,0.0008080449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002367968,0.0004360759,0.5983492,0.0004988887,0.004766192,0.0002983756,0.002233395,0.165646,0.001072559,0.02572435,0.001437103,0.1971699],"study_design_scores_gemma":[0.0001995298,0.0007470926,0.09326993,0.0002180266,0.0005528367,0.0003302043,0.0003240585,0.8600613,0.001082459,0.04226438,0.0008265919,0.0001236235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4761223,0.0006428254,0.5191214,0.0006878837,0.00005169071,0.0005948552,0.0002542669,0.0004878803,0.002036921],"genre_scores_gemma":[0.9214186,0.00007949466,0.07759811,0.0001210408,0.00001467759,0.0003933093,0.0002047987,0.00004123519,0.0001286426],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1382416,"threshold_uncertainty_score":0.7311001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6519117362826303,"score_gpt":0.4294619938330695,"score_spread":0.2224497424495608,"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."}}