{"id":"W2064379877","doi":"10.1177/0013164402238082","title":"A Monte Carlo Comparison of Item and Person Statistics Based on Item Response Theory versus Classical Test Theory","year":2002,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Item response theory; Classical test theory; Monte Carlo method; Statistics; Psychology; Econometrics; Psychometrics; Test theory; Item analysis; Computerized adaptive testing; Test (biology); Differential item functioning; Statistical hypothesis testing; Mathematics","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":[],"category_scores_codex":[0.01027207,0.0001819323,0.0003530799,0.0002524895,0.0001913847,0.00008219505,0.0002878135,0.0001049792,0.001011047],"category_scores_gemma":[0.172042,0.0001161324,0.00006305706,0.000536033,0.0003283359,0.00004402149,0.00002999475,0.0002453282,0.00002152588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005421782,"about_ca_system_score_gemma":0.00003108215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002247613,"about_ca_topic_score_gemma":0.000001370805,"domain_scores_codex":[0.9951723,0.002010999,0.0005431725,0.0005771259,0.001464459,0.000231893],"domain_scores_gemma":[0.8836055,0.1152891,0.0002623309,0.0003207914,0.0003424304,0.0001797696],"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":[0.01164811,0.006034489,0.2767802,0.00003284093,0.00008277433,0.000007231965,0.002875438,0.0001539937,0.001107383,0.02980219,0.06665417,0.6048211],"study_design_scores_gemma":[0.001347528,0.002614317,0.9663729,0.00004826986,0.00002579324,0.000005199957,0.002115086,0.0057995,0.00002630321,0.01839773,0.003043179,0.0002042159],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747216,0.002340278,0.00535482,0.007777893,0.001234807,0.0003116508,0.00009027667,0.00002997171,0.008138726],"genre_scores_gemma":[0.9894863,0.00001688989,0.009530709,0.0003684703,0.0001058357,0.00002270557,0.000001019333,0.000006495478,0.0004615909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6895927,"threshold_uncertainty_score":0.9999022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7790233134897627,"score_gpt":0.505780321916664,"score_spread":0.2732429915730987,"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."}}