{"id":"W4378220707","doi":"10.1177/00131644231165520","title":"The Accuracy of Bayesian Model Fit Indices in Selecting Among Multidimensional Item Response Theory Models","year":2023,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Curse of dimensionality; Nested set model; Deviance information criterion; Bayesian probability; Item response theory; Statistics; Bayesian information criterion; Computer science; Mathematics; Econometrics; Bayesian inference; Data mining; Psychometrics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.03375351,0.0001376236,0.0002274767,0.0004037244,0.0003423304,0.00007638348,0.0004799435,0.00008811115,0.00007409475],"category_scores_gemma":[0.1342375,0.00007556276,0.00007315091,0.00194178,0.0002031168,0.0001560064,0.0001087669,0.0002411598,0.00001082533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004232831,"about_ca_system_score_gemma":0.0001052791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001190186,"about_ca_topic_score_gemma":0.00001014214,"domain_scores_codex":[0.9952661,0.001589994,0.0007658458,0.0005152998,0.001548965,0.000313745],"domain_scores_gemma":[0.9243127,0.07451524,0.0003582073,0.0003234392,0.0003836709,0.0001068015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00372423,0.001448302,0.4741755,0.0000242338,0.0001051602,0.00000752765,0.005528371,0.06979506,0.005134942,0.07053924,0.01974472,0.3497727],"study_design_scores_gemma":[0.0002068253,0.00006301989,0.6286461,0.00002852264,0.000002477598,0.000002911229,0.0007493426,0.04117201,0.00002646136,0.3288742,0.0001486045,0.00007955189],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865698,0.0005475775,0.004657246,0.00619546,0.0003898258,0.0002297609,0.000005434059,0.00002556682,0.00137938],"genre_scores_gemma":[0.9950299,0.00006015572,0.004220119,0.0002142838,0.00005613844,0.00005772978,0.00000113072,0.000005704479,0.0003548242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3496931,"threshold_uncertainty_score":0.9949541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7180011966789275,"score_gpt":0.5115401562574108,"score_spread":0.2064610404215167,"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."}}