{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04339649,0.001033863,0.001226441,0.009163097,0.0006829954,0.004670768,0.001471392,0.00145226,0.003420649],"category_scores_gemma":[0.17624,0.0003370776,0.001570862,0.007322065,0.001610456,0.004032248,0.002428999,0.001924938,0.001351627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002130138,"about_ca_system_score_gemma":0.00176599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001305096,"about_ca_topic_score_gemma":0.001607282,"domain_scores_codex":[0.9479811,0.03645249,0.0038254,0.00138038,0.009746374,0.0006141915],"domain_scores_gemma":[0.8472014,0.1199909,0.008324559,0.006960807,0.01671018,0.0008121657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002041943,0.001139192,0.1803217,0.001075189,0.0007259836,0.0001570436,0.004814392,0.03045269,0.001789077,0.08034903,0.008778763,0.6901928],"study_design_scores_gemma":[0.0003561981,0.004224301,0.320914,0.002857245,0.0004318709,0.001121471,0.01565909,0.2767255,0.008473374,0.299978,0.06858903,0.0006698622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.234611,0.002348512,0.7009992,0.003197948,0.000456961,0.004598121,0.001724204,0.001287763,0.05077626],"genre_scores_gemma":[0.4826855,0.001158635,0.506171,0.0005711629,0.0001095543,0.005266155,0.001834797,0.0001350841,0.002068012],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04339649,"threshold_uncertainty_score":0.2295053,"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."}}