{"id":"W2036299295","doi":"10.1177/0013164405275668","title":"A Comparison of Four Methods for Detecting Differential Item Functioning in Ordered Response Items","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Ottawa","funders":"","keywords":"Differential item functioning; Statistics; Psychology; Logistic regression; Item response theory; Type I and type II errors; Linear discriminant analysis; Ordinal regression; Skewness; Ordered logit; Discriminant function analysis; Sample (material); Psychometrics; 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"],"consensus_categories":[],"category_scores_codex":[0.01660389,0.000134141,0.0003899913,0.0004020942,0.0001638882,0.00007330627,0.0002766927,0.00009501773,0.000329475],"category_scores_gemma":[0.123021,0.00009296528,0.00009579861,0.0008843424,0.00006671863,0.00007808873,0.00004428082,0.0001724039,0.00000419145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006617919,"about_ca_system_score_gemma":0.00004288567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008133952,"about_ca_topic_score_gemma":0.00001028462,"domain_scores_codex":[0.9961089,0.001427582,0.0009758526,0.0005150642,0.0007266143,0.0002459678],"domain_scores_gemma":[0.9650272,0.03378924,0.0003946032,0.0002350469,0.000459236,0.0000946554],"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":[0.001067661,0.0006333358,0.1681289,0.000008109153,0.00001717727,7.877512e-8,0.0005126914,0.0001314781,0.02222869,0.0003845797,0.0007858325,0.8061015],"study_design_scores_gemma":[0.0008067818,0.0004340136,0.9704582,0.00003370296,0.000008449601,0.000006885484,0.0007167471,0.002786707,0.0007629854,0.01714009,0.006710089,0.0001353615],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7998247,0.0007578594,0.1947046,0.003047766,0.0008755152,0.0002670674,0.000002289899,0.00001288854,0.0005073022],"genre_scores_gemma":[0.8085319,0.000003805697,0.1909927,0.00008508631,0.0002025916,0.00007145528,7.896008e-7,0.000004391317,0.0001073229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8059661,"threshold_uncertainty_score":0.8843662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8267139799800711,"score_gpt":0.6035828191741548,"score_spread":0.2231311608059163,"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."}}