{"id":"W2170853093","doi":"10.1111/j.1745-3992.2003.tb00136.x","title":"Using Multidimensional Item Response Theory to Evaluate Educational and Psychological Tests","year":2003,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":192,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Item response theory; Test (biology); Measure (data warehouse); Ninth; Computer science; Process (computing); Meaning (existential); Multidimensional analysis; Psychology; Mathematics education; Psychometrics; Management science; Econometrics; Mathematics; Data mining; Developmental psychology; Psychotherapist","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05058032,0.0001947472,0.0002388297,0.0003752727,0.0004601169,0.0002583107,0.000209834,0.0000757461,0.001204988],"category_scores_gemma":[0.6463413,0.0001460503,0.0000420616,0.0009438032,0.0001126364,0.0004408504,0.00007613112,0.000183248,0.00009124365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009356135,"about_ca_system_score_gemma":0.0003446095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002454763,"about_ca_topic_score_gemma":0.000001745588,"domain_scores_codex":[0.9904012,0.00588029,0.0005715716,0.0007551193,0.002108174,0.000283652],"domain_scores_gemma":[0.8754453,0.1217538,0.0003417781,0.0004156052,0.00171895,0.0003245768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0105423,0.005656771,0.2253975,0.00004733429,0.0003970318,0.00001585365,0.008179787,0.0007752535,0.07944028,0.4385619,0.08696332,0.1440227],"study_design_scores_gemma":[0.0005090386,0.0002813728,0.6620944,0.00005153928,0.00005219252,0.0004490313,0.002137011,0.00009915711,0.0001408088,0.1328589,0.2010121,0.0003144805],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.913103,0.007822783,0.003829669,0.06630247,0.001771152,0.0004524864,0.000007636509,0.00002046664,0.006690371],"genre_scores_gemma":[0.6327977,0.00006669179,0.3634975,0.002033121,0.000256745,0.00003090728,0.000001416599,0.00001156304,0.001304368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.595761,"threshold_uncertainty_score":0.9997081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8128600435609681,"score_gpt":0.6116511900217015,"score_spread":0.2012088535392665,"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."}}