{"id":"W2618796793","doi":"10.1007/978-3-319-56129-5_4","title":"Ecological Framework of Item Responding as Validity Evidence: An Application of Multilevel DIF Modeling Using PISA Data","year":2017,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Ecological validity; Item response theory; Multilevel model; Test (biology); Psychology; Context (archaeology); Cognition; Process (computing); Cognitive psychology; Ecology; Computer science; Psychometrics; Machine learning; Developmental psychology; Geography","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":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004271584,0.0003490241,0.0007722215,0.0007453757,0.00101424,0.00009025427,0.002699738,0.001536933,0.001927726],"category_scores_gemma":[0.002081851,0.0003181768,0.0001670144,0.0001961847,0.001799152,0.0005211218,0.0009472004,0.001859856,0.00007630741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067835,"about_ca_system_score_gemma":0.0006286463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003998264,"about_ca_topic_score_gemma":0.00002363651,"domain_scores_codex":[0.9951388,0.0007900919,0.0008840488,0.001141487,0.001462819,0.0005827036],"domain_scores_gemma":[0.9944676,0.001922155,0.001028452,0.001788175,0.0005660937,0.0002275251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001401118,0.001003549,0.01006535,0.0003636179,0.0004641404,0.00002254913,0.007460221,0.000008780432,0.0006514866,0.9586624,0.001006516,0.0188903],"study_design_scores_gemma":[0.0005159699,0.001441357,0.04086564,0.001388818,0.0002106025,0.00001574658,0.004681203,0.0007356371,0.0001128637,0.9259892,0.02292755,0.001115459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8299731,0.001166273,0.003410616,0.001460563,0.00159222,0.002670458,0.002215124,0.0001229415,0.1573887],"genre_scores_gemma":[0.9718893,0.0002617208,0.002162646,0.00004165455,0.00115857,0.0000911831,0.0004320338,0.0000662937,0.02389658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1419162,"threshold_uncertainty_score":0.999927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6791328271668623,"score_gpt":0.6122680313743544,"score_spread":0.06686479579250793,"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."}}