{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2127215,0.0001257912,0.0007431371,0.001719712,0.0003759418,0.00007458187,0.001075176,0.00006482597,0.0001031321],"category_scores_gemma":[0.803913,0.0001010182,0.000228354,0.004120781,0.0001272016,0.0002755988,0.0008957471,0.0004194504,6.821211e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001129525,"about_ca_system_score_gemma":0.0003166044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009998423,"about_ca_topic_score_gemma":0.00006645709,"domain_scores_codex":[0.954888,0.03565532,0.002963924,0.0007802629,0.005210277,0.0005021863],"domain_scores_gemma":[0.1451148,0.8492672,0.001850258,0.001728035,0.00187879,0.0001608835],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007691375,0.00130441,0.8650081,0.00007325228,0.00008875145,0.00000465991,0.01060577,0.08159809,0.001034265,0.0004265383,0.00007747671,0.03208732],"study_design_scores_gemma":[0.001907392,0.0009333311,0.7389119,0.00001705556,0.000006691895,6.62295e-7,0.05372586,0.04496948,0.0001911004,0.1590818,0.0001002018,0.0001545164],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9396953,0.0002148737,0.05818878,0.000183114,0.0001349101,0.00140617,0.0001331483,0.00001614404,0.0000275503],"genre_scores_gemma":[0.9944376,0.000002305597,0.005330947,0.00003595341,0.00001093944,0.0001324797,0.000005247688,0.00001156594,0.00003301441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8136119,"threshold_uncertainty_score":0.8106689,"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."}}