{"id":"W2096343999","doi":"10.1191/0265532203lt248oa","title":"Does item-level DIF manifest itself in scale-level analyses? Implications for translating language tests","year":2003,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Equivalence (formal languages); Psychology; Scale (ratio); Measurement invariance; Item response theory; Item analysis; Statistics; Test (biology); Psychometrics; Developmental psychology; Linguistics; Structural equation modeling; Mathematics; Confirmatory factor analysis","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":[0.006747382,0.0003296185,0.0006064455,0.0008460847,0.0003819273,0.0003147263,0.0008995,0.0001509855,0.0001260107],"category_scores_gemma":[0.2575959,0.0002099897,0.0001911787,0.004788593,0.00007689429,0.0003262023,0.00008801077,0.0003267178,0.0000220619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006955244,"about_ca_system_score_gemma":0.0000954463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004920563,"about_ca_topic_score_gemma":0.001119523,"domain_scores_codex":[0.9958195,0.0005375626,0.001269155,0.0009708789,0.0005923416,0.0008105782],"domain_scores_gemma":[0.9392038,0.05879252,0.0005797765,0.0009333737,0.0003084515,0.0001821001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007264762,0.00009430339,0.6871116,0.00003705266,0.00001642013,0.00002815883,0.004096707,0.0001968023,0.05214192,0.0004318964,0.0001117143,0.2557262],"study_design_scores_gemma":[0.001122805,0.00007757432,0.9640663,0.0001531694,0.00004474372,0.00008866646,0.01552727,0.003763278,0.002878072,0.01148491,0.0001887571,0.0006045162],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9085241,0.000791975,0.07255301,0.0005000946,0.0003716465,0.0006680805,0.0002236013,0.0002721901,0.0160953],"genre_scores_gemma":[0.6726789,0.000001488572,0.3261494,0.0001705375,0.0001277178,0.00006777591,0.00001047682,0.00003100654,0.0007626727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2769547,"threshold_uncertainty_score":0.8563132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6773012489253456,"score_gpt":0.5390986227521983,"score_spread":0.1382026261731473,"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."}}