{"id":"W2063611796","doi":"10.1080/15305058.2011.617475","title":"Methodologies for Investigating Item- and Test-Level Measurement Equivalence in International Large-Scale Assessments","year":2012,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Comparability; Psychology; Item response theory; Equivalence (formal languages); Statistics; Nonparametric statistics; Test (biology); Psychometrics; Consistency (knowledge bases); Item analysis; Logistic regression; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03423003,0.0001699518,0.0003777544,0.0009512466,0.00009910401,0.0002991174,0.001320366,0.00007479876,0.0000382111],"category_scores_gemma":[0.6310325,0.0001306996,0.0001127948,0.0006482329,0.00007769925,0.001089666,0.0004233571,0.000315677,0.000002437312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002263224,"about_ca_system_score_gemma":0.0001260458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002093083,"about_ca_topic_score_gemma":0.000007369788,"domain_scores_codex":[0.9949619,0.0004122212,0.001518275,0.0002838765,0.002419526,0.0004041574],"domain_scores_gemma":[0.8772222,0.1157515,0.002426522,0.00023604,0.004127027,0.0002367326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002370454,0.00008440615,0.8363786,0.000006062034,0.00004110663,0.000005538834,0.0003843894,0.0001581708,0.006958658,0.0001928567,0.0003240832,0.1554424],"study_design_scores_gemma":[0.001385228,0.0002099137,0.9500422,0.0004051996,0.00001986312,0.0003014881,0.002868365,0.01228085,0.001264212,0.02952302,0.001481325,0.0002183349],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6880037,0.0007646934,0.3023771,0.001690685,0.005024903,0.0001876176,0.00004462444,0.00002465008,0.001882109],"genre_scores_gemma":[0.5284334,0.00001264457,0.4708877,0.0001639493,0.000451001,0.000005564054,6.236936e-7,0.000007271503,0.00003780019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5968025,"threshold_uncertainty_score":0.9944634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.84777911019985,"score_gpt":0.5833143230805201,"score_spread":0.2644647871193299,"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."}}