{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01141557,0.0001226615,0.0004903222,0.0007854021,0.0001600543,0.00008047854,0.0007831053,0.00006265773,0.00006681073],"category_scores_gemma":[0.4145085,0.00005796462,0.0001420349,0.005386302,0.0001277264,0.0001335543,0.0001973834,0.00009879949,0.00001295402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003562884,"about_ca_system_score_gemma":0.00004165266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003062233,"about_ca_topic_score_gemma":0.0000231855,"domain_scores_codex":[0.99466,0.002977157,0.0008459082,0.0003780026,0.0008827788,0.00025622],"domain_scores_gemma":[0.6935288,0.3045207,0.0006976206,0.0007427942,0.0004498233,0.0000602253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002412629,0.000642151,0.5015641,0.00000692805,0.0008781728,0.00002183377,0.0005707229,0.0006212259,0.05612699,0.001064591,0.00005357862,0.4360371],"study_design_scores_gemma":[0.00101454,0.0003096149,0.8575367,0.0002476108,0.0002776879,0.000005409556,0.0003859779,0.03424765,0.004298618,0.1013579,0.00005600202,0.0002621845],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9464118,0.0004343764,0.05222957,0.0004821846,0.00005521669,0.0002000833,0.00001858689,0.0000326673,0.0001355546],"genre_scores_gemma":[0.9060541,0.00001467427,0.0936441,0.00005623343,0.00002876353,0.00001534803,4.075824e-7,0.000006536926,0.0001798235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4357749,"threshold_uncertainty_score":0.5904233,"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."}}