{"id":"W2046847367","doi":"10.1177/0013164414523618","title":"Binary Logistic Regression Analysis for Detecting Differential Item Functioning","year":2014,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Differential item functioning; Sample size determination; Type I and type II errors; Logistic regression; Mathematics; Statistical power; Statistical hypothesis testing; Regression analysis; Psychology; Econometrics; Item response theory; 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":[0.006831338,0.0001584821,0.0003356064,0.0004603774,0.0004966154,0.0001785681,0.000298738,0.00009305454,0.0006398659],"category_scores_gemma":[0.08741688,0.000093968,0.0001874974,0.001396662,0.00008093782,0.00006725208,0.00005648179,0.0001412909,0.00001544253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004066225,"about_ca_system_score_gemma":0.00001646653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000073227,"about_ca_topic_score_gemma":0.000003272663,"domain_scores_codex":[0.9968578,0.0005254154,0.0005716039,0.0007165021,0.001065428,0.0002632361],"domain_scores_gemma":[0.9817921,0.01688142,0.0003224482,0.0003404165,0.0005095615,0.0001540392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002587307,0.0006081151,0.5362867,0.00001685102,0.0002151928,3.655031e-7,0.0001416307,0.0004374408,0.003788019,0.005098598,0.005178716,0.4479697],"study_design_scores_gemma":[0.0003164504,0.0003164578,0.9364413,0.00001710218,0.00008326254,0.000003941901,0.0001314025,0.003382031,0.00002667797,0.05620732,0.002932264,0.0001417942],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6241598,0.000291252,0.3697023,0.002141013,0.001655448,0.0001741304,0.000003616303,0.00003370863,0.001838674],"genre_scores_gemma":[0.9831123,0.000006904824,0.01571086,0.0002268991,0.0005591488,0.00006898479,0.00000663633,0.00000504428,0.0003032273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4478279,"threshold_uncertainty_score":0.9202702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7639754128351917,"score_gpt":0.5122407613224709,"score_spread":0.2517346515127208,"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."}}