{"id":"W2956271099","doi":"10.1111/jedm.12207","title":"Performance of Person‐Fit Statistics Under Model Misspecification","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Statistic; Econometrics; Item response theory; Inference; Latent variable; Latent variable model; Parametric statistics; Statistics; Statistical inference; Goodness of fit; Parametric model; Computer science; Variable (mathematics); Specification; Empirical research; Aggregate (composite); Mathematics; Psychometrics; Artificial intelligence","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008058826,0.00007989928,0.0002415795,0.000402391,0.00004820295,0.00003962346,0.000471546,0.00003235048,0.001177689],"category_scores_gemma":[0.01666983,0.00005668306,0.00008133424,0.0005419796,0.00003362056,0.000194784,0.00001564193,0.0001285421,0.0000492205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001686499,"about_ca_system_score_gemma":0.0006504118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002589893,"about_ca_topic_score_gemma":5.970788e-7,"domain_scores_codex":[0.9960083,0.0001535621,0.0008529919,0.0001470224,0.002717496,0.000120587],"domain_scores_gemma":[0.9914179,0.003660943,0.001275297,0.0002622162,0.003299369,0.00008428025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003259794,0.001036471,0.6190682,0.00008985038,0.0001842954,3.722452e-7,0.001416414,0.1701382,0.02813555,0.02166417,0.0733558,0.08458471],"study_design_scores_gemma":[0.0004109372,0.0002556197,0.9447799,0.00006640283,0.00002382397,0.0000204139,0.00114099,0.02984292,0.0006597081,0.0217014,0.0009865317,0.0001113041],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9530818,0.000552744,0.03478964,0.002992226,0.001445564,0.000112098,0.000008475073,0.000001748896,0.007015693],"genre_scores_gemma":[0.9067581,0.00003277836,0.09219344,0.00007008282,0.0001338315,0.000001086741,5.114379e-7,0.000004749691,0.0008054746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3257118,"threshold_uncertainty_score":0.9997354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7529540980675968,"score_gpt":0.4796196803409436,"score_spread":0.2733344177266532,"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."}}