{"id":"W3161167275","doi":"10.1093/oxfordhb/9780190092689.013.7","title":"Test Theory and Measurement in Assessment","year":2021,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Item response theory; Classical test theory; Scale (ratio); Test (biology); Psychology; Reliability (semiconductor); Construct validity; Jargon; Construct (python library); Field (mathematics); Cognitive psychology; Computer science; Data science; Social psychology; Psychometrics; Mathematics; Linguistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.006855515,0.0002614821,0.0005426079,0.0006003932,0.0001446567,0.0001523491,0.0007191142,0.0002564293,0.0001376085],"category_scores_gemma":[0.006999792,0.0002371751,0.0001317177,0.00005981044,0.0001642054,0.00008025044,0.0008005658,0.0004874617,5.402183e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002138915,"about_ca_system_score_gemma":0.000174851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002242394,"about_ca_topic_score_gemma":0.00003633162,"domain_scores_codex":[0.9968578,0.0004138547,0.0003901168,0.0007597067,0.001326877,0.0002516872],"domain_scores_gemma":[0.986224,0.01223288,0.0003713302,0.0006806157,0.000363276,0.0001279204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003876521,0.0000184194,0.001030286,0.00001793735,0.0000456782,0.0002446162,0.00008586839,0.000004360919,0.00002485537,0.8481604,0.0008434093,0.1494854],"study_design_scores_gemma":[0.0004409486,0.00005884474,0.002785185,0.0001531337,0.00004177739,0.000009143289,0.0003209902,0.00003754615,0.00001306689,0.03730356,0.958571,0.000264772],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002458837,0.0004358472,0.003885389,0.00003133526,0.0002354682,0.0002191487,0.0000310927,0.00003426027,0.9948816],"genre_scores_gemma":[0.003719252,0.0003517645,0.004749957,0.00006021283,0.00004636213,6.472191e-7,0.00000253768,0.00001845536,0.9910508],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9577276,"threshold_uncertainty_score":0.9671719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3806889262478403,"score_gpt":0.3734058047044967,"score_spread":0.007283121543343651,"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."}}