{"id":"W2965434934","doi":"10.5539/ies.v12n8p59","title":"Detecting Gender Differences in PISA 2012 Mathematics Test with Differential Item Functioning","year":2019,"lang":"en","type":"article","venue":"International Education Studies","topic":"Education, Achievement, and Giftedness","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Differential item functioning; Context (archaeology); Logistic regression; Item response theory; Multilevel model; Test (biology); Sample (material); Test validity; Construct validity; Construct (python library); Social psychology; Psychometrics; Developmental psychology; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005041868,0.0004666903,0.0004244336,0.001454196,0.0003358368,0.0007736344,0.0004834136,0.0003968002,0.003724257],"category_scores_gemma":[0.01661207,0.0002143587,0.0007961903,0.0008537605,0.0004705794,0.0006366619,0.0007284762,0.0005652687,0.0007140475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003641026,"about_ca_system_score_gemma":0.0004178145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009175359,"about_ca_topic_score_gemma":0.001581665,"domain_scores_codex":[0.9968222,0.001079614,0.0004024832,0.0003905233,0.001020948,0.000284108],"domain_scores_gemma":[0.9908956,0.003972011,0.002394907,0.000843195,0.001566649,0.0003275578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001610121,0.00006994956,0.9736966,0.00004646945,0.00009073469,0.00007861912,0.0006676506,0.0001558154,0.001193749,0.0003117017,0.0005207109,0.02300691],"study_design_scores_gemma":[0.00001022102,0.0002243371,0.9953361,0.00003158882,0.00003986436,0.0002451621,0.0005938743,0.0008584699,0.001392527,0.000314641,0.0009456673,0.000007587741],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940539,0.0001775746,0.002033622,0.0001152388,0.00003825794,0.00004776905,0.0003215627,0.00002600871,0.003185992],"genre_scores_gemma":[0.9973686,0.00004405523,0.001506677,0.00002859561,0.000009202599,0.00005648135,0.0003686791,0.00001165415,0.0006061753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005041868,"threshold_uncertainty_score":0.02666426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09779288800822464,"score_gpt":0.3959092010579396,"score_spread":0.298116313049715,"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."}}