{"id":"W2132885336","doi":"","title":"Comparison and Properties of Correlational and Agreement Methods for Determining Whether or Not to Report Subtest Scores","year":2014,"lang":"en","type":"article","venue":"International Journal of Learning Teaching and Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Statistics; Estimator; Scale (ratio); Test (biology); Psychology; Population; Econometrics; Clinical psychology; Mathematics; Medicine; Geography; Cartography; Environmental health","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4389991,0.001843045,0.001602435,0.007945891,0.001866853,0.004656557,0.002881358,0.002960817,0.001742168],"category_scores_gemma":[0.7931219,0.001614918,0.002977983,0.00610344,0.005451536,0.007957326,0.004176088,0.00358579,0.001109954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002573388,"about_ca_system_score_gemma":0.003564104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002200242,"about_ca_topic_score_gemma":0.002657314,"domain_scores_codex":[0.4432323,0.4612728,0.02609597,0.016964,0.05096448,0.00147042],"domain_scores_gemma":[0.04077076,0.8925749,0.01849209,0.02828284,0.01941499,0.0004644028],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004572135,0.0007352197,0.4332677,0.002506508,0.009610304,0.0002825052,0.01038336,0.02795322,0.003012283,0.07701203,0.006345024,0.4243198],"study_design_scores_gemma":[0.001514937,0.005356255,0.3216816,0.002947407,0.003370008,0.00206563,0.00620983,0.504286,0.01355434,0.1208839,0.01703668,0.001093435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1832198,0.0034185,0.7950984,0.001161054,0.0006691266,0.002664722,0.001107744,0.001066918,0.01159374],"genre_scores_gemma":[0.6772274,0.00106863,0.3152263,0.0003134643,0.0002529698,0.003507217,0.0006817147,0.0004265119,0.001295801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5610008,"threshold_uncertainty_score":0.6918139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7641883607625612,"score_gpt":0.6669834294211824,"score_spread":0.09720493134137886,"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."}}