{"id":"W4393304410","doi":"10.31274/td-20240329-47","title":"Advances in random forest tuning and improvements in false discovery rate controlling procedures via test-specific covariate adjustments","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Plant Sciences Institute, Iowa State University; National Institute of Food and Agriculture; Genome Alberta; Genome Canada","keywords":"Covariate; False discovery rate; Multiple comparisons problem; Null hypothesis; Type I and type II errors; Null (SQL); Statistics; Random forest; Null model; Statistical hypothesis testing; Sample size determination; Data mining; Mathematics; Variance (accounting); Computer science; Artificial intelligence; Biology","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":[0.05827805,0.002914561,0.003442582,0.00389651,0.001396172,0.002982066,0.005942641,0.002965922,0.003925052],"category_scores_gemma":[0.1834378,0.001471869,0.00388681,0.004392082,0.002244898,0.004546707,0.002902516,0.007200269,0.002079399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001794138,"about_ca_system_score_gemma":0.004116639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004576648,"about_ca_topic_score_gemma":0.00377621,"domain_scores_codex":[0.9623233,0.02235536,0.00195388,0.00575193,0.006928994,0.0006865889],"domain_scores_gemma":[0.873415,0.09565082,0.00515567,0.01544541,0.009618716,0.0007142939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005160901,0.0003407392,0.008083739,0.001072569,0.0009818381,0.0002463816,0.0005284129,0.1171982,0.009338632,0.08752526,0.007498465,0.7666696],"study_design_scores_gemma":[0.0002438441,0.0004258036,0.004588923,0.0003213807,0.0003949037,0.0004337206,0.00006975418,0.8191985,0.009333674,0.1428612,0.02188459,0.0002437699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001181089,0.0009166945,0.9962001,0.0002071639,0.00009987255,0.00007552996,0.00007912693,0.0007894498,0.0004509457],"genre_scores_gemma":[0.04931264,0.001708948,0.9447616,0.0005320965,0.0006043622,0.0006359487,0.0004474866,0.0008494723,0.001147495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05827805,"threshold_uncertainty_score":0.3082074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008214222595270113,"score_gpt":0.2689927436560605,"score_spread":0.2607785210607904,"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."}}