{"id":"W3113373418","doi":"10.1080/10627197.2020.1858783","title":"The Effect of Linguistic Factors on Assessment of English Language Learners’ Mathematical Ability: A Differential Item Functioning Analysis","year":2020,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Differential item functioning; Ell; Psychology; Achievement test; Test (biology); Standardized test; Mathematics education; Language proficiency; Item response theory; Confirmatory factor analysis; Item analysis; Language assessment; Linguistics; Psychometrics; Developmental psychology; Teaching method; Mathematics; Statistics; Vocabulary development","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006599482,0.0002357532,0.0005961654,0.00009519693,0.0001445568,0.00004940426,0.0002265208,0.00005431426,0.001161973],"category_scores_gemma":[0.01127857,0.0001464612,0.0003429452,0.0004475724,0.0001212321,0.00004188597,0.0001050981,0.0002453617,0.000007069213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001457123,"about_ca_system_score_gemma":0.0001667226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000686083,"about_ca_topic_score_gemma":0.000003103994,"domain_scores_codex":[0.9976732,0.0002821066,0.0006906986,0.0003026577,0.0008398209,0.0002115881],"domain_scores_gemma":[0.983105,0.01586777,0.0003470766,0.000263818,0.0002794437,0.0001368707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002426313,0.004504393,0.3974387,0.002974872,0.007652943,0.000005019893,0.04445623,0.0001240053,0.002513358,0.5350029,0.001227586,0.003857311],"study_design_scores_gemma":[0.002277644,0.002812012,0.8395072,0.0005499497,0.003876051,0.00000123381,0.01615151,0.008579496,0.01413989,0.1109964,0.0001702828,0.0009384319],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981694,0.00001133264,0.007758553,0.0004567842,0.0002388313,0.0004598537,0.00002751372,0.00003312917,0.009319987],"genre_scores_gemma":[0.9959021,0.00000170601,0.003550489,0.00002304731,0.000240064,0.00006823341,0.00005544656,0.00001831148,0.0001405692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4420684,"threshold_uncertainty_score":0.9997511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02162447829000549,"score_gpt":0.3490916083046128,"score_spread":0.3274671300146073,"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."}}