{"id":"W2625675150","doi":"10.5539/jel.v6n4p113","title":"Examination of Different Item Response Theory Models on Tests Composed of Testlets","year":2017,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Statistics; Item response theory; Sample size determination; Psychology; Mathematics; Sample (material); Psychometrics","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":[],"category_scores_codex":[0.01366301,0.00006395211,0.0002595096,0.0005742817,0.0001896064,0.00008692681,0.0003308614,0.00004011663,0.00004369672],"category_scores_gemma":[0.1803129,0.00004125679,0.00006105223,0.0001741961,0.00007953151,0.0002238227,0.00003800441,0.0002287355,7.00509e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001782458,"about_ca_system_score_gemma":0.00008673836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002816474,"about_ca_topic_score_gemma":2.240217e-7,"domain_scores_codex":[0.9970924,0.001608582,0.0005965447,0.0001058232,0.0005260224,0.00007063719],"domain_scores_gemma":[0.9623167,0.03441411,0.002358017,0.0002356326,0.0006149648,0.00006058372],"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":[0.0005050296,0.0003127833,0.09364677,0.00001472409,0.00001764039,8.289461e-7,0.003629121,0.001000859,0.01437176,0.002815396,0.0001668786,0.8835182],"study_design_scores_gemma":[0.0002772371,0.000449711,0.9798874,0.0001536459,0.000008910814,0.00001516277,0.003459887,0.001575165,0.0008399406,0.01306392,0.0002268939,0.00004209601],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923288,0.0001913687,0.003209998,0.0003223613,0.0004260893,0.00003869291,3.591784e-7,0.000002181305,0.003480204],"genre_scores_gemma":[0.9957978,0.00002827678,0.003125394,0.00002437689,0.0000585252,4.213078e-7,1.502566e-7,0.000003724279,0.0009613908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8862407,"threshold_uncertainty_score":0.8265917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4463604006241616,"score_gpt":0.5023882591824396,"score_spread":0.05602785855827797,"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."}}