{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2831473,0.001685141,0.002795767,0.009645748,0.0007734505,0.004376698,0.003176507,0.002372331,0.006707405],"category_scores_gemma":[0.5785996,0.000814014,0.004200751,0.004932922,0.005442849,0.006470828,0.004595218,0.002655801,0.0006767204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001809064,"about_ca_system_score_gemma":0.001246189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004062358,"about_ca_topic_score_gemma":0.0002944522,"domain_scores_codex":[0.6938615,0.2651159,0.0125706,0.007918072,0.01947602,0.001057895],"domain_scores_gemma":[0.3614603,0.5787924,0.01387793,0.02860053,0.01622714,0.001041695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006689505,0.0008788242,0.082348,0.006144334,0.007450565,0.0003228353,0.008059801,0.03617782,0.00784832,0.2927403,0.006120402,0.5452193],"study_design_scores_gemma":[0.002877319,0.01800943,0.2465201,0.005475199,0.007240993,0.001663565,0.007087232,0.3160987,0.02077991,0.3453749,0.02756812,0.00130457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1108289,0.003375586,0.8689085,0.0006394912,0.0003757113,0.002711447,0.00109387,0.0009651435,0.01110127],"genre_scores_gemma":[0.6286783,0.0005624779,0.3639965,0.0002993806,0.0001140245,0.004834724,0.0006942198,0.0003589564,0.0004614204],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2831473,"threshold_uncertainty_score":0.884007,"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."}}