{"id":"W2287543214","doi":"10.1016/j.amar.2016.02.001","title":"Multilevel Dirichlet process mixture analysis of railway grade crossing crash data","year":2016,"lang":"en","type":"article","venue":"Analytic Methods in Accident Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Transport Canada","keywords":"Latent Dirichlet allocation; Outlier; Computer science; Parametric statistics; Bayesian probability; Dirichlet process; Crash; Multilevel model; Bayes' theorem; Probabilistic logic; Dirichlet distribution; Econometrics; Statistical model; Bayesian hierarchical modeling; Bayes factor; Data mining; Statistics; Machine learning; Mathematics; Artificial intelligence; Topic model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01544522,0.0007455706,0.001910627,0.003450458,0.001089411,0.002711591,0.003234023,0.00221175,0.005359423],"category_scores_gemma":[0.05675909,0.001011873,0.003249058,0.00334833,0.001324903,0.003105683,0.003548031,0.003497979,0.00098522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001710862,"about_ca_system_score_gemma":0.001618095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008461903,"about_ca_topic_score_gemma":0.01004347,"domain_scores_codex":[0.989917,0.006644751,0.0004610219,0.001444511,0.001042991,0.0004897444],"domain_scores_gemma":[0.9440391,0.04776281,0.001804132,0.00425491,0.001733014,0.0004060646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001129548,0.0003652399,0.03613663,0.0004684007,0.001139584,0.0003379257,0.001800918,0.4565652,0.003632034,0.3195494,0.006717043,0.1721581],"study_design_scores_gemma":[0.00002952354,0.00003977035,0.007591761,0.00005093394,0.000101627,0.00007751538,0.0001520185,0.8883167,0.0005654928,0.1012513,0.00176735,0.0000560546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07770442,0.0005027854,0.9185319,0.000741843,0.00006912301,0.0001021235,0.001002786,0.0003433342,0.001001682],"genre_scores_gemma":[0.7767866,0.000701157,0.2122176,0.0001994042,0.0002415731,0.0006470134,0.004537545,0.0003236643,0.004345556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01544522,"threshold_uncertainty_score":0.0816831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2801242802163502,"score_gpt":0.5646036332053688,"score_spread":0.2844793529890186,"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."}}