{"id":"W4308426657","doi":"10.1111/jedm.12347","title":"A Unified Comparison of IRT‐Based Effect Sizes for DIF Investigations","year":2022,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Differential item functioning; Estimator; Statistics; Item response theory; Sample size determination; Differential (mechanical device); Population; Sample (material); Monte Carlo method; Econometrics; Computer science; Mathematics; Psychometrics","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"],"consensus_categories":[],"category_scores_codex":[0.01895082,0.00008853992,0.0003911719,0.0006583376,0.000275096,0.00004406178,0.0006119709,0.00002002647,0.0004649803],"category_scores_gemma":[0.1505744,0.00006447136,0.0002217139,0.001204847,0.0000555772,0.00008341571,0.00004305578,0.0001781681,0.000001520206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171558,"about_ca_system_score_gemma":0.0009982039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007568528,"about_ca_topic_score_gemma":0.000002715785,"domain_scores_codex":[0.9947153,0.0009318049,0.001198713,0.0001542066,0.002866399,0.0001335339],"domain_scores_gemma":[0.9580836,0.03766682,0.001899433,0.0002452324,0.001983688,0.0001212769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005644303,0.001653287,0.7779037,0.00006694494,0.0001984594,4.980901e-7,0.0009492635,0.05203756,0.02159172,0.006310406,0.1122784,0.0264453],"study_design_scores_gemma":[0.003874741,0.004676634,0.7382927,0.000157792,0.0002124151,0.00003105726,0.003768564,0.006675349,0.01444881,0.1730152,0.05449144,0.0003552587],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9480686,0.001715119,0.02715563,0.01742548,0.003949674,0.0005232892,0.00003112977,0.000005636044,0.001125414],"genre_scores_gemma":[0.9549753,7.219386e-7,0.04459525,0.000139375,0.0001703093,0.0000410286,0.000001993457,0.000005366847,0.00007065936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1667048,"threshold_uncertainty_score":0.8565807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6842492147562678,"score_gpt":0.529819503327333,"score_spread":0.1544297114289348,"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."}}