{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07414579,0.00195068,0.0016835,0.004217158,0.000659171,0.003300453,0.002712016,0.00160585,0.002576016],"category_scores_gemma":[0.2421288,0.0008349232,0.003942812,0.00428615,0.001738618,0.003383651,0.002024223,0.002075242,0.001113332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002756553,"about_ca_system_score_gemma":0.001755971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002589474,"about_ca_topic_score_gemma":0.001841872,"domain_scores_codex":[0.9138171,0.06468005,0.003039488,0.005179647,0.01219455,0.001089141],"domain_scores_gemma":[0.7240615,0.2414999,0.008076981,0.01360752,0.01212281,0.0006311694],"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":[0.002701207,0.002107618,0.5064,0.001448217,0.004018764,0.0006626825,0.007919887,0.1318959,0.003987176,0.02221446,0.002820705,0.3138235],"study_design_scores_gemma":[0.0002808796,0.004147834,0.2750654,0.0006865731,0.0009938214,0.0008471649,0.005099223,0.6715248,0.006469727,0.03080335,0.003775061,0.0003061302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7203243,0.0005190237,0.2717208,0.0004027167,0.0001266949,0.0009495203,0.0006240233,0.000609084,0.004723814],"genre_scores_gemma":[0.9145525,0.000269377,0.08127853,0.0001420106,0.000034784,0.001158965,0.001656159,0.0001371712,0.0007705329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07414579,"threshold_uncertainty_score":0.3921251,"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."}}