{"id":"W4412520505","doi":"10.1007/s11136-025-04018-6","title":"Tree-based latent variable model for assessing differential item functioning in patient-reported outcome measures: a simulation study","year":2025,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trinity Western University; University of British Columbia; Western University; University of Manitoba; University of Saskatchewan; University of Alberta; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Bonferroni correction; Type I and type II errors; Statistics; Polytomous Rasch model; Mathematics; Differential item functioning; Statistical power; Multiple comparisons problem; Econometrics; Item response theory; Psychometrics","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":[0.05819755,0.0001384102,0.0006799563,0.001922222,0.000365207,0.0003412073,0.0005095196,0.0001230761,0.00003591405],"category_scores_gemma":[0.4679148,0.0001084746,0.0001469639,0.004364814,0.00008726754,0.0002365389,0.0001954705,0.0003721844,0.000001197113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000166967,"about_ca_system_score_gemma":0.0005794026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008704342,"about_ca_topic_score_gemma":0.0001173967,"domain_scores_codex":[0.9885125,0.004636766,0.002492229,0.0007073628,0.003164137,0.0004869615],"domain_scores_gemma":[0.8098242,0.1851292,0.0008920811,0.001082413,0.002916203,0.0001559433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003904589,0.0006274839,0.7890794,0.00005381287,0.00003336416,6.643778e-7,0.0003483887,0.1748409,0.0004638874,0.0002618914,0.00004423724,0.03385558],"study_design_scores_gemma":[0.001239242,0.00009329333,0.3844737,0.00003761526,0.000006608643,2.201057e-8,0.002173935,0.6056856,0.00001815073,0.006191584,0.00001504218,0.00006522732],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5409067,0.00002734858,0.4578937,0.0001228597,0.0001546153,0.0005773751,0.000004036826,0.00001912138,0.0002943193],"genre_scores_gemma":[0.9861307,4.667742e-7,0.01347318,0.00003668804,0.00002568852,0.00007820732,0.000004072149,0.000008689293,0.0002423396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.445224,"threshold_uncertainty_score":0.9697838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9128303773161305,"score_gpt":0.6416932658765836,"score_spread":0.2711371114395469,"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."}}