{"id":"W4382516807","doi":"10.31234/osf.io/p2n8a","title":"Comparing the Accuracy of Three Predictive Information Criteria for Bayesian Linear Multilevel Model Selection","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Overfitting; Deviance information criterion; Akaike information criterion; Bayesian information criterion; Model selection; Information Criteria; Leverage (statistics); Computer science; Multilevel model; Bayesian probability; Selection (genetic algorithm); Deviance (statistics); Data mining; Context (archaeology); Linear model; Machine learning; Artificial intelligence; Econometrics; Statistics; Bayesian inference; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0009228974,0.0002492528,0.0004997249,0.0001165149,0.0001290005,0.00008415044,0.0003589903,0.0002507999,0.00003740164],"category_scores_gemma":[0.006269516,0.0001729546,0.0001501212,0.0001016703,0.00007289876,0.0001961336,0.00036934,0.0004181674,0.000005387595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006269032,"about_ca_system_score_gemma":0.0001640283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001557206,"about_ca_topic_score_gemma":0.00008844137,"domain_scores_codex":[0.998356,0.0000862745,0.0008144067,0.0002358503,0.0002744852,0.0002330163],"domain_scores_gemma":[0.9945486,0.003916288,0.0005540435,0.0003802139,0.0005490629,0.00005178446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003334075,0.0001361556,0.0006623185,0.004105135,0.0003305,2.194565e-7,0.003264139,0.01156635,0.0001409903,0.9423433,0.006149007,0.03096847],"study_design_scores_gemma":[0.0001438459,0.00002804751,0.0007184572,0.0001401284,0.00006580762,4.072227e-7,0.0000540572,0.5205965,0.0002708577,0.477879,0.000006666584,0.0000962522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009771145,0.000002165427,0.9954063,0.0001647382,0.0003126256,0.001551412,0.000519005,0.0001878247,0.0008787707],"genre_scores_gemma":[0.1862066,0.000005441117,0.8131754,0.0000297332,0.0001005344,0.000346348,0.00006246828,0.00002603526,0.00004742899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5090302,"threshold_uncertainty_score":0.7505649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2668533767769755,"score_gpt":0.4405836038420233,"score_spread":0.1737302270650479,"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."}}