{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0430287,0.00008673425,0.0002818285,0.0009705829,0.0003483511,0.0002896161,0.0003762463,0.00004415776,0.0000412117],"category_scores_gemma":[0.4258193,0.00005706758,0.00004365955,0.000210766,0.0001617059,0.0001978604,0.0002042372,0.0005603347,9.606606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000430124,"about_ca_system_score_gemma":0.000208759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005445501,"about_ca_topic_score_gemma":0.000003061525,"domain_scores_codex":[0.9956926,0.001655096,0.0008732156,0.0002618315,0.00134844,0.0001688187],"domain_scores_gemma":[0.913164,0.08361878,0.0007292099,0.000122948,0.002194925,0.0001701184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004689362,0.00007115002,0.5576235,0.0000175211,0.00005591111,0.000001276094,0.003324128,0.0006469046,0.005453239,0.001469205,0.0008373237,0.4300309],"study_design_scores_gemma":[0.000794646,0.001145887,0.9212993,0.0006008858,0.00001885754,0.0008034591,0.006119225,0.02422713,0.000974563,0.01249683,0.03133276,0.0001864257],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.917543,0.0003389084,0.07565917,0.005480823,0.0004915749,0.00009856107,0.000001382429,0.000002658697,0.0003839464],"genre_scores_gemma":[0.7863569,0.00001920184,0.2118317,0.00004374952,0.0002847868,0.000005345419,0.000001023747,0.000005982783,0.001451277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4298445,"threshold_uncertainty_score":0.9854034,"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."}}