{"id":"W4311193885","doi":"10.1155/2022/2833537","title":"Random Forests in Count Data Modelling: An Analysis of the Influence of Data Features and Overdispersion on Regression Performance","year":2022,"lang":"en","type":"article","venue":"Journal of Probability and Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Farm Service Agency; Deutscher Akademischer Austauschdienst; International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete; Carnegie Corporation of New York","keywords":"Overdispersion; Statistics; Mathematics; Generalized linear model; Negative binomial distribution; Categorical variable; Random forest; Poisson distribution; Regression analysis; Linear regression; Covariate; Regression; Quasi-likelihood; Count data; Poisson regression; Sample size determination; Mean squared error; Artificial intelligence; Computer science; Population","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.1030345,0.002176232,0.002223469,0.002990657,0.001110361,0.00263588,0.002048635,0.002009559,0.0007997798],"category_scores_gemma":[0.1812165,0.0007961531,0.003049185,0.003386651,0.001940872,0.003866925,0.001911128,0.002726683,0.0004102194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001021304,"about_ca_system_score_gemma":0.001427516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004406922,"about_ca_topic_score_gemma":0.002629931,"domain_scores_codex":[0.9514239,0.03621515,0.002330208,0.004781113,0.004290534,0.0009590542],"domain_scores_gemma":[0.6522933,0.3150142,0.01234489,0.01322387,0.00630104,0.0008228371],"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":[0.001519654,0.0002285568,0.138121,0.0009068933,0.002191543,0.000859633,0.00116517,0.6921306,0.004362746,0.008629202,0.001886629,0.1479984],"study_design_scores_gemma":[0.00004483855,0.0004054469,0.01827404,0.000205339,0.0003463479,0.0004141057,0.0001665641,0.9657349,0.003719683,0.008946726,0.001631069,0.0001110183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3243032,0.004524139,0.6671332,0.0006607547,0.00017641,0.0002918759,0.0005391077,0.001258914,0.00111255],"genre_scores_gemma":[0.8438126,0.0009365221,0.1528153,0.0001986623,0.0001264984,0.0003898212,0.0009045791,0.0003793933,0.0004365295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1030345,"threshold_uncertainty_score":0.5449049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1191788818123905,"score_gpt":0.3858918382672176,"score_spread":0.2667129564548271,"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."}}