{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03213668,0.003615539,0.004501236,0.008764946,0.001403502,0.00868287,0.004737963,0.004283709,0.02024074],"category_scores_gemma":[0.1192265,0.00178292,0.002934332,0.01095294,0.007374236,0.007412996,0.00650194,0.01139254,0.0178189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002176724,"about_ca_system_score_gemma":0.007333084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001822258,"about_ca_topic_score_gemma":0.001223151,"domain_scores_codex":[0.9621179,0.02456734,0.003063285,0.003130852,0.006640645,0.000480041],"domain_scores_gemma":[0.8642259,0.1061578,0.004045074,0.01751081,0.00658792,0.001472359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001234788,0.00008229526,0.001188677,0.003747583,0.000696582,0.0004643217,0.0008640618,0.01111404,0.0009439522,0.630055,0.1250202,0.2256998],"study_design_scores_gemma":[0.00006240916,0.00004727615,0.0005221869,0.0008505712,0.00006776596,0.0002442632,0.0001158743,0.0140261,0.0003484969,0.7972913,0.1863542,0.00006955688],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004380588,0.01513737,0.9534352,0.009525912,0.002617168,0.0005103017,0.002046578,0.005093526,0.01119595],"genre_scores_gemma":[0.01515337,0.0205534,0.9402451,0.00390729,0.005675843,0.004494267,0.002752846,0.002644511,0.004573401],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03213668,"threshold_uncertainty_score":0.169957,"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."}}