{"id":"W4390048276","doi":"10.1007/s11136-023-03560-5","title":"Unsupervised item response theory models for assessing sample heterogeneity in patient-reported outcomes measures","year":2023,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Saskatchewan; Trinity Western University; University of British Columbia; University of Calgary; McGill University; Western University; University of Lethbridge; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Item response theory; Quality of Life Research; Sample (material); Psychology; Public health; Psychometrics; Econometrics; Medicine; Clinical psychology; Economics; Nursing","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2555481,0.0001679097,0.0008457779,0.002385068,0.0002914339,0.0002657648,0.001110647,0.0001637097,0.00003965125],"category_scores_gemma":[0.8575521,0.0001237064,0.0002876801,0.006342916,0.0003045665,0.0003944369,0.0004686207,0.0003625284,0.0000109858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008631972,"about_ca_system_score_gemma":0.0004979247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007683785,"about_ca_topic_score_gemma":0.00007962212,"domain_scores_codex":[0.9675355,0.02347838,0.00241641,0.0008924152,0.004775397,0.0009018923],"domain_scores_gemma":[0.2672885,0.7279221,0.0006664412,0.001649979,0.002161222,0.0003116767],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002319323,0.000183685,0.8849608,0.00006931223,0.00006367067,0.000008225948,0.002122603,0.001747658,0.002880379,0.001939071,0.0006407988,0.1030645],"study_design_scores_gemma":[0.0008349025,0.0001148674,0.7257165,0.00003341115,0.000002421466,5.845158e-7,0.007813731,0.01018518,0.0005184233,0.2543506,0.0002844732,0.0001449569],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9576885,0.0001970994,0.03973634,0.001232873,0.0001809513,0.0006033755,0.00007342386,0.00008018579,0.0002072425],"genre_scores_gemma":[0.9877689,0.0000175112,0.01189832,0.0000842455,0.00002545924,0.00007603364,0.000006742999,0.00001886667,0.000103886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7044438,"threshold_uncertainty_score":0.7665699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9246502373271043,"score_gpt":0.6511370832006224,"score_spread":0.2735131541264819,"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."}}