{"id":"W2128422078","doi":"10.4310/sii.2016.v9.n4.a1","title":"Statistical methods and computing for big data","year":2016,"lang":"en","type":"article","venue":"Statistics and Its Interface","topic":"Data Analysis with R","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Cancer Institute; Banff International Research Station for Mathematical Innovation and Discovery; National Institutes of Health; National Science Foundation","keywords":"Big data; Computational statistics; Software; Scale (ratio); Selection (genetic algorithm); Data stream mining; Feature selection","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":[0.0007033164,0.0001144992,0.0001898421,0.00004904661,0.00009456071,0.0001837393,0.0006434027,0.00002769857,0.000008335666],"category_scores_gemma":[0.0009653349,0.00007761057,0.000006599635,0.00007092964,0.000073132,0.0002282912,0.001188088,0.00004940128,0.000007958027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001005696,"about_ca_system_score_gemma":0.00002986496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009180972,"about_ca_topic_score_gemma":0.00001216615,"domain_scores_codex":[0.998836,0.00008920198,0.0002268852,0.00052307,0.0001067807,0.0002180843],"domain_scores_gemma":[0.9975086,0.001662271,0.00007948667,0.0005478832,0.00008952541,0.0001122058],"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":[0.000005871071,0.00001100667,0.00007089998,0.00003017366,0.00003512947,0.000002350452,0.00009242668,8.657678e-7,0.001125982,0.2016233,0.01297766,0.7840243],"study_design_scores_gemma":[0.0007970812,0.0002571278,0.001889689,0.00008371219,0.00007235798,0.00002535003,0.00003719201,0.8884582,0.002125189,0.04055085,0.06532338,0.0003799097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003943291,0.0003304838,0.9955162,0.0004309678,0.0003464059,0.00009981904,0.002790856,0.00002847651,0.00006244813],"genre_scores_gemma":[0.1128695,0.00006902484,0.8866372,0.00008578092,0.00006482994,0.000001589104,0.0000338329,0.000008436217,0.0002297765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8884573,"threshold_uncertainty_score":0.3164867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1010523441108938,"score_gpt":0.4147756650059232,"score_spread":0.3137233208950294,"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."}}