{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002694224,0.00008994791,0.000438007,0.00009950624,0.0001006845,0.00001526777,0.0005446743,0.00003297129,0.00001301056],"category_scores_gemma":[0.001854318,0.00005451965,0.0000219734,0.000257476,0.0001833514,0.000210872,0.0004635557,0.0003025048,7.809778e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003006905,"about_ca_system_score_gemma":0.00008691718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005369588,"about_ca_topic_score_gemma":0.0001390173,"domain_scores_codex":[0.9982298,0.0004074574,0.0006078758,0.0001947669,0.0004690012,0.00009108331],"domain_scores_gemma":[0.9967036,0.001800269,0.0005878428,0.0007152142,0.0001450844,0.00004802238],"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":[0.004716999,0.001611085,0.3498017,0.001978904,0.0004332858,0.00002121598,0.003731526,0.124996,0.0002339897,0.4650295,0.0005908915,0.04685483],"study_design_scores_gemma":[0.0005741866,0.000314324,0.2047559,0.0001377922,0.000344303,0.0000103635,0.0001299847,0.5367615,0.00001406211,0.2568849,0.00001123829,0.00006144679],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6472641,0.0000545976,0.3509596,0.00003719307,0.00002115262,0.0001066882,0.001551086,7.939742e-7,0.0000047301],"genre_scores_gemma":[0.6014379,0.00008944774,0.3984387,0.000008888595,0.000004534043,5.888123e-7,0.00001593338,0.000002640915,0.000001391249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4117655,"threshold_uncertainty_score":0.2223247,"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."}}