{"id":"W2989790728","doi":"10.1289/isesisee.2018.p03.0660","title":"Selecting the Best Method among Several: Bayesian and Classical Data Analyses Comparison in a Complex Microbiological Validation Setting","year":2018,"lang":"en","type":"article","venue":"ISEE Conference Abstracts","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada","funders":"","keywords":"Bayesian probability; Prior probability; Statistics; Credibility; Null hypothesis; Equivalence (formal languages); Statistical power; Ranking (information retrieval); Null (SQL); Statistical hypothesis testing; Computer science; Expert elicitation; Bayesian statistics; Mathematics; Data mining; Bayesian inference; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003441461,0.0002185693,0.0004365588,0.0001367808,0.0004110328,0.0007005419,0.001190962,0.0001262987,0.00009978539],"category_scores_gemma":[0.01273341,0.0001407972,0.0000279232,0.0006122176,0.0005526581,0.0008120909,0.0005574451,0.0005220457,0.00005387038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004097201,"about_ca_system_score_gemma":0.00009008479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001933431,"about_ca_topic_score_gemma":0.0006840071,"domain_scores_codex":[0.9964778,0.0005789354,0.0009902413,0.0009300297,0.0005737011,0.0004492649],"domain_scores_gemma":[0.9918513,0.006317917,0.0005004336,0.0007081902,0.0004702788,0.0001518275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002421738,0.0004713839,0.3393584,0.00005096734,0.00009902129,0.00007830559,0.005312303,0.04300182,0.08420505,0.002059742,0.003541646,0.5215793],"study_design_scores_gemma":[0.0003664711,0.0001115037,0.7609563,0.00008126508,0.00003527473,0.00002131989,0.003788107,0.2122304,0.004035299,0.0168396,0.001183774,0.0003506908],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5485587,0.00003098774,0.4489731,0.0007494467,0.0001134626,0.0002114017,0.00003745788,0.00004235264,0.001283081],"genre_scores_gemma":[0.9299641,0.000003149402,0.06967565,0.00008225605,0.0001739697,0.000005933591,0.00003788872,0.00000986821,0.00004723056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5212286,"threshold_uncertainty_score":0.9955828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5498383607141563,"score_gpt":0.5631727966915318,"score_spread":0.01333443597737549,"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."}}