{"id":"W2095820822","doi":"10.3102/1076998610397052","title":"Sampling Variability and Axioms of Classical Test Theory","year":2011,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Statistics; Sampling (signal processing); Sample size determination; Statistical hypothesis testing; Test theory; Sample (material); Test (biology); Axiom; Reliability (semiconductor); Population; Applied mathematics; Psychometrics; Computer science; Geometry","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":[0.05315699,0.001001787,0.002575294,0.003622723,0.001789615,0.004700808,0.004469867,0.002484474,0.003777306],"category_scores_gemma":[0.2204103,0.0009779917,0.002196445,0.002954523,0.01354864,0.006757646,0.005487541,0.006206825,0.001098517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002844684,"about_ca_system_score_gemma":0.002794921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003161281,"about_ca_topic_score_gemma":0.001403925,"domain_scores_codex":[0.9454123,0.02581417,0.003626024,0.008717971,0.01527478,0.001154712],"domain_scores_gemma":[0.7803366,0.177596,0.006936162,0.02102841,0.01326101,0.0008417424],"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":[0.00004228337,0.00003965172,0.003227971,0.0001799852,0.0001002532,0.0001257433,0.0006232903,0.01305515,0.0002898854,0.9496275,0.001559565,0.03112869],"study_design_scores_gemma":[0.00003492427,0.00004273868,0.00165175,0.0001081217,0.00002574418,0.0002002632,0.000068418,0.03201616,0.0003694598,0.9615014,0.003943918,0.00003709803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008071425,0.0006852314,0.9799565,0.001215434,0.0001868702,0.0001484118,0.0002264343,0.000182438,0.009327265],"genre_scores_gemma":[0.4291905,0.001995763,0.5564993,0.002003162,0.001377793,0.002803,0.0009638516,0.0003358985,0.004830698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05315699,"threshold_uncertainty_score":0.2811244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6043028112079372,"score_gpt":0.5189607433140067,"score_spread":0.0853420678939305,"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."}}