{"id":"W2669206880","doi":"10.1080/01621459.2018.1505626","title":"MCMC for Imbalanced Categorical Data","year":2018,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Computer science; Markov chain Monte Carlo; Bayesian probability; Approximate Bayesian computation; Computational complexity theory; Computation; Sample size determination; Sample (material); Bayesian inference; Logarithm; Machine learning; Data mining; Algorithm; Artificial intelligence; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009613751,0.001092027,0.001560565,0.002855642,0.001463263,0.002272919,0.003434905,0.001992215,0.005973953],"category_scores_gemma":[0.07177188,0.001311241,0.001366731,0.004106001,0.002533005,0.003327314,0.002756859,0.005249647,0.001598739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003022813,"about_ca_system_score_gemma":0.003412998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009907124,"about_ca_topic_score_gemma":0.0129612,"domain_scores_codex":[0.9941925,0.00311721,0.0002452265,0.000919105,0.001281488,0.0002443858],"domain_scores_gemma":[0.9623518,0.02795421,0.001872843,0.005565414,0.001770016,0.000485718],"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":[0.0003579856,0.0001179575,0.006069031,0.0004484323,0.000223965,0.0002144218,0.0005211295,0.3921404,0.002048453,0.4656089,0.015585,0.1166643],"study_design_scores_gemma":[0.00002785619,0.000009321043,0.0004708826,0.00003461183,0.00001111704,0.00003617823,0.0000231241,0.7714573,0.000613822,0.2244498,0.00285073,0.00001533081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004883062,0.0003358849,0.9917279,0.0005415546,0.00005823232,0.00009642535,0.0005207965,0.000813906,0.001022219],"genre_scores_gemma":[0.1856751,0.0006409171,0.8060017,0.0006248931,0.0002750914,0.0008653895,0.002772094,0.0005595987,0.002585274],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009907124,"threshold_uncertainty_score":0.050843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03988550071863376,"score_gpt":0.3559444286280251,"score_spread":0.3160589279093913,"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."}}