{"id":"W2055526333","doi":"10.7202/1025005ar","title":"Item response theory in educational assessment and evaluation","year":2014,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Equating; Item response theory; Polytomous Rasch model; Differential item functioning; Item bank; Variance (accounting); Test (biology); Computerized adaptive testing; Classical test theory; Econometrics; Computer science; Educational assessment; Psychology; Psychometrics; Statistics; Mathematics education; Mathematics; Rasch model; Clinical psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3340422,0.0001332326,0.0002124368,0.0009387367,0.0001300142,0.0001990686,0.0002598817,0.0001007927,0.0007186264],"category_scores_gemma":[0.325814,0.0001107108,0.00004118229,0.001398086,0.00004397123,0.00053805,0.00005168249,0.0001826578,0.00004390108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003384941,"about_ca_system_score_gemma":0.0009625778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001958001,"about_ca_topic_score_gemma":0.00003672371,"domain_scores_codex":[0.946663,0.04925878,0.0009052948,0.000681777,0.002274224,0.0002169278],"domain_scores_gemma":[0.8542752,0.1436973,0.0004994633,0.0005831738,0.0008706583,0.00007417727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001437644,0.000174353,0.4126337,0.000006972188,0.0000115008,9.491755e-8,0.01804205,0.001821611,0.001687751,0.03848671,0.001994898,0.5249965],"study_design_scores_gemma":[0.0003931704,0.00004346281,0.7475491,0.00001447683,0.00001134752,0.000003091361,0.0009429592,0.03235268,0.00002403215,0.2177966,0.0007770443,0.00009201436],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9319968,0.0001161035,0.04554487,0.01281178,0.001003497,0.0004337846,0.000001905637,0.00002361024,0.008067596],"genre_scores_gemma":[0.9793664,0.00001455352,0.0195155,0.0003136171,0.0001197539,0.0001094927,0.00002978106,0.000009916996,0.0005210461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5249045,"threshold_uncertainty_score":0.7868456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5154681060706208,"score_gpt":0.5912371517400445,"score_spread":0.07576904566942377,"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."}}