{"id":"W4401129858","doi":"10.20944/preprints202407.2197.v1","title":"Comparison of Statistical and Machine Learning Methods for Analysing Traffic Accident Fatalities","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Traffic and Road Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Standard deviation; Statistics; Speed limit; Logistic regression; Attendance; Confidence interval; Mathematics; Regression analysis; Standard error; Quarter (Canadian coin); Random forest; Econometrics; Engineering; Geography; Computer science; Transport engineering; Artificial intelligence; Economics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01826295,0.001174322,0.001105185,0.00734866,0.0004028929,0.001611351,0.0007892339,0.001088264,0.00141005],"category_scores_gemma":[0.03931885,0.0003108416,0.00147376,0.004190918,0.000418004,0.001390471,0.0006721299,0.0009055574,0.0007316351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008638848,"about_ca_system_score_gemma":0.00130788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003873492,"about_ca_topic_score_gemma":0.003024933,"domain_scores_codex":[0.986104,0.008600388,0.0009988715,0.001020028,0.002863961,0.000412791],"domain_scores_gemma":[0.9215547,0.06997575,0.001802507,0.001896043,0.004378695,0.0003923105],"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":[0.002425137,0.0006012589,0.1271212,0.001066598,0.00190052,0.0002386431,0.0005928493,0.1367521,0.00250057,0.003628305,0.004670268,0.7185025],"study_design_scores_gemma":[0.0001762281,0.001385857,0.1212296,0.0003337148,0.0005217841,0.0005597777,0.0008690226,0.8567582,0.004033943,0.008836991,0.005118916,0.0001758963],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.519176,0.01088922,0.4537376,0.00116257,0.0006856472,0.0005958379,0.002865717,0.003779838,0.007107564],"genre_scores_gemma":[0.8242373,0.002090421,0.1688144,0.0001060817,0.0002423728,0.0005531205,0.001898289,0.0002046938,0.001853223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01826295,"threshold_uncertainty_score":0.09658486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1506534175075079,"score_gpt":0.4336247923269774,"score_spread":0.2829713748194695,"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."}}