{"id":"W2977609233","doi":"10.1002/bimj.201800146","title":"Latent variable models for harmonization of test scores: A case study on memory","year":2019,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McMaster University; Impact","funders":"FP7 Health","keywords":"Equating; Harmonization; Test (biology); Observational study; Latent variable; Econometrics; Reliability (semiconductor); Statistics; Variable (mathematics); Computer science; Mathematics; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009827354,0.0001144781,0.0003204827,0.0005888178,0.00007547576,0.0000593665,0.0001384171,0.00006744284,0.0001236812],"category_scores_gemma":[0.004604952,0.00008161642,0.00007192314,0.001266063,0.0000230118,0.00008212442,0.00003367306,0.0001614881,0.000007301755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000601184,"about_ca_system_score_gemma":0.0000646304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001458455,"about_ca_topic_score_gemma":2.333836e-7,"domain_scores_codex":[0.9986675,0.0001084748,0.0004902836,0.0001683323,0.0003649979,0.0002004195],"domain_scores_gemma":[0.9944551,0.004657974,0.0002387963,0.0001787485,0.0003330667,0.0001363375],"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":[0.0009640264,0.02515404,0.04677385,0.001256891,0.0008199262,0.002273624,0.002674947,0.0004361268,0.01155385,0.6200654,0.00697963,0.2810477],"study_design_scores_gemma":[0.004133031,0.006933316,0.001561197,0.000211971,0.0002442189,0.001524514,0.001006127,0.0730294,0.001438162,0.9095098,0.00003751298,0.000370696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1022244,0.00002341478,0.8966843,0.00002628188,0.0001930574,0.0004933323,0.00004329071,0.00001244844,0.0002994148],"genre_scores_gemma":[0.5735074,0.000003173621,0.4263339,0.00001962326,0.00005705437,0.000007308538,5.088539e-7,0.00001244092,0.00005862661],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.471283,"threshold_uncertainty_score":0.551289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.161248548609808,"score_gpt":0.3960955340183089,"score_spread":0.2348469854085009,"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."}}