{"id":"W2617028377","doi":"10.1007/978-3-319-56129-5_18","title":"National and International Educational Achievement Testing: A Case of Multi-level Validation Framed by the Ecological Model of Item Responding","year":2017,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Learning Partnership; University of British Columbia","funders":"","keywords":"Multilevel model; Construct (python library); Scale (ratio); Multilevel modelling; Test (biology); Construct validity; Rank (graph theory); Psychology; Process (computing); Achievement test; Computer science; Mathematics education; Statistics; Mathematics; Psychometrics; Geography; Ecology; Standardized test; Developmental psychology","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":[0.08608753,0.0005934188,0.0008830375,0.003294697,0.007415414,0.01125351,0.004067237,0.005126508,0.002680063],"category_scores_gemma":[0.1188261,0.0009567072,0.0009049674,0.005423287,0.01557807,0.01251209,0.009966528,0.008288203,0.0004857502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01101007,"about_ca_system_score_gemma":0.01324194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07270918,"about_ca_topic_score_gemma":0.1028194,"domain_scores_codex":[0.9392581,0.0417277,0.002345091,0.003017618,0.009979782,0.003671822],"domain_scores_gemma":[0.8676736,0.09962454,0.003665823,0.01620202,0.01075071,0.002083289],"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":[0.0001218976,0.0001732351,0.08284943,0.0001097858,0.00004547883,0.00347485,0.09613397,0.00136104,0.0004331907,0.686788,0.008994455,0.1195147],"study_design_scores_gemma":[0.00008740393,0.0003100825,0.1450919,0.002978771,0.0001820683,0.007559914,0.1373255,0.02363446,0.004525801,0.5411473,0.1368011,0.0003555036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3639531,0.003952834,0.1449841,0.05559386,0.000736875,0.0008791808,0.000501405,0.0003903406,0.4290083],"genre_scores_gemma":[0.9138161,0.0005586889,0.0694823,0.002197563,0.00008076573,0.0003924315,0.0002198629,0.00015269,0.01309958],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08608753,"threshold_uncertainty_score":0.4552798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3195819131446898,"score_gpt":0.4698414348904325,"score_spread":0.1502595217457428,"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."}}