{"id":"W4283080197","doi":"10.1007/s11136-022-03169-0","title":"Accuracy of mixture item response theory models for identifying sample heterogeneity in patient-reported outcomes: a simulation study","year":2022,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Trinity Western University; Western University; University of Manitoba; University of Saskatchewan; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Quality of Life Research; Item response theory; Sample (material); Public health; Psychology; Econometrics; Medicine; Psychometrics; Clinical psychology; Economics; Nursing","routes":{"ca_aff":true,"ca_fund":true,"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":[],"category_scores_codex":[0.1989417,0.001660236,0.002565222,0.002512736,0.001262934,0.003570418,0.003480537,0.004703928,0.002113208],"category_scores_gemma":[0.5091417,0.001257103,0.004361875,0.001730002,0.003342079,0.004980233,0.002872725,0.003764724,0.0004495103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002700017,"about_ca_system_score_gemma":0.002076189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008638182,"about_ca_topic_score_gemma":0.003086339,"domain_scores_codex":[0.8921145,0.09858859,0.002358189,0.003621772,0.002476089,0.0008408483],"domain_scores_gemma":[0.1601448,0.8169999,0.005331283,0.01323941,0.003564559,0.0007200848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01523307,0.002280225,0.2191665,0.0006271419,0.004895467,0.0004299047,0.004338699,0.6553243,0.0007751376,0.02157668,0.001932103,0.07342073],"study_design_scores_gemma":[0.0005901032,0.001155761,0.0153977,0.0001476116,0.0006488748,0.0001954762,0.0003490515,0.9690667,0.0003738164,0.01169258,0.0002939961,0.00008832577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8262318,0.0007068007,0.1689082,0.001026973,0.00007410815,0.0007216511,0.0004635526,0.0002742356,0.00159264],"genre_scores_gemma":[0.9635021,0.000119553,0.03515353,0.0002095322,0.00001720079,0.0004027603,0.0003104432,0.00005654858,0.0002283213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1989417,"threshold_uncertainty_score":0.9878475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9013700084845456,"score_gpt":0.6644036239285863,"score_spread":0.2369663845559593,"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."}}