{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05293211,0.001324476,0.002010938,0.006502772,0.002293461,0.005564445,0.003391775,0.001264441,0.005667554],"category_scores_gemma":[0.1311325,0.001413824,0.003708632,0.009276498,0.004494402,0.004772141,0.005975346,0.004362024,0.0008692622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003104488,"about_ca_system_score_gemma":0.005810289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01095826,"about_ca_topic_score_gemma":0.01385479,"domain_scores_codex":[0.9449096,0.04685339,0.001332333,0.002921164,0.003499548,0.0004838861],"domain_scores_gemma":[0.8839392,0.09720222,0.003148892,0.009612612,0.00544293,0.0006540882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001221087,0.0002537636,0.08923825,0.0005246578,0.001003817,0.0002637095,0.008574337,0.02124691,0.0006727873,0.6652451,0.006687993,0.2061666],"study_design_scores_gemma":[0.00003813327,0.0002422196,0.02922155,0.0004283774,0.0003935465,0.0005104353,0.003620371,0.2326757,0.0006179749,0.7223269,0.009811635,0.0001131632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01822801,0.0003810764,0.9730783,0.001008261,0.00007281737,0.0003437446,0.0004904218,0.0003395375,0.006057846],"genre_scores_gemma":[0.2514822,0.00043746,0.7441273,0.0002227914,0.00006898097,0.001544081,0.0005589599,0.0002601098,0.001298087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05293211,"threshold_uncertainty_score":0.2799351,"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."}}