{"id":"W2089004370","doi":"10.1080/00273171.2014.911075","title":"Assessing Approximate Fit in Categorical Data Analysis","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":276,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Statistics; Categorical variable; Goodness of fit; Bivariate analysis; Statistic; Ordinal data; Mean squared error; Multivariate statistics; Item response theory; Cutoff; Econometrics; 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","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06789506,0.00019378,0.0006847961,0.003695402,0.0003645494,0.001568493,0.003915066,0.0001948321,0.0004574907],"category_scores_gemma":[0.1353053,0.0001387953,0.0001248472,0.01809684,0.0002166894,0.001025268,0.00237268,0.0009957455,0.0001513954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381085,"about_ca_system_score_gemma":0.0001155104,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00768937,"about_ca_topic_score_gemma":0.0002825699,"domain_scores_codex":[0.9877265,0.005116583,0.001031515,0.001591223,0.003483151,0.001051025],"domain_scores_gemma":[0.9401888,0.05426135,0.000291132,0.004070431,0.0008200483,0.0003682886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003253505,0.0003797802,0.5946727,0.000003554449,0.00002128683,0.00005240723,0.0002381581,0.0003247374,0.001274263,0.0006026227,0.0003631779,0.4020348],"study_design_scores_gemma":[0.0004344537,0.00006212924,0.6948122,0.00000672899,0.00003637165,0.000003376153,0.0008846339,0.2945472,0.00005222311,0.008106944,0.0008746418,0.0001790714],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8743252,0.00005339425,0.120998,0.0003043569,0.0002561329,0.000262758,0.00001853803,0.000063156,0.003718504],"genre_scores_gemma":[0.9463621,0.000004795175,0.05303899,0.00001360396,0.00009085159,0.00002121219,0.00003299737,0.00001622875,0.0004191595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4018557,"threshold_uncertainty_score":0.999468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.959382260741685,"score_gpt":0.7182746444274037,"score_spread":0.2411076163142812,"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."}}