{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003550463,0.0001612314,0.0002373504,0.0005685264,0.002188395,0.0001740008,0.0005605408,0.0003531153,0.0004558641],"category_scores_gemma":[0.004977623,0.0001401815,0.00007535465,0.0001407842,0.002413149,0.0002485003,0.0002603017,0.0005625781,0.000008466485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004226937,"about_ca_system_score_gemma":0.004856014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003078803,"about_ca_topic_score_gemma":0.000385128,"domain_scores_codex":[0.9972283,0.0002515976,0.0004670166,0.0003146997,0.001466831,0.0002715947],"domain_scores_gemma":[0.9966677,0.001210206,0.0006190854,0.0001406466,0.001235165,0.0001271542],"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":[0.00005836155,0.0002435537,0.002037866,0.000043782,0.0002026792,0.000002897992,0.04536581,0.000004853781,0.00008843185,0.9271519,0.01596885,0.00883102],"study_design_scores_gemma":[0.0020815,0.0004439478,0.071222,0.0006472945,0.0001323521,0.0000519205,0.04129814,0.0003319441,0.0007007811,0.6416981,0.2397086,0.001683447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2264171,0.0006093852,0.00009117009,0.06266108,0.001088636,0.0027133,0.002348855,0.0000678666,0.7040026],"genre_scores_gemma":[0.6480854,0.0002134191,0.001726638,0.00005801476,0.0004368985,0.00008253351,0.0001654599,0.00002300216,0.3492087],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4216683,"threshold_uncertainty_score":0.9991106,"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."}}