{"id":"W3166788073","doi":"10.1002/9781118445112.stat08122","title":"Principal Component Analysis for Big Data","year":2018,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Principal component analysis; Big data; Dimensionality reduction; Computer science; Kernel principal component analysis; Subspace topology; Data science; Causal inference; Sparse PCA; Inference; Factor analysis; Data mining; Focus (optics); Artificial intelligence; Dimension (graph theory); Analytics; Data analysis; Statistical inference; Ranking (information retrieval); Machine learning; Kernel method; Mathematics; Econometrics; Statistics; Support vector machine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005900585,0.002324234,0.00181352,0.005490803,0.001035837,0.003689477,0.002418436,0.002032217,0.01148774],"category_scores_gemma":[0.03272724,0.0007673798,0.001960553,0.008966905,0.00251456,0.002589042,0.003867129,0.005743914,0.006982164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001578775,"about_ca_system_score_gemma":0.003508243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00367715,"about_ca_topic_score_gemma":0.002708875,"domain_scores_codex":[0.9919648,0.003785643,0.0004971658,0.001199471,0.002390578,0.0001623528],"domain_scores_gemma":[0.9841328,0.009448327,0.001407254,0.002739249,0.001985834,0.0002866187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000649865,0.00008858922,0.002435966,0.001667831,0.0004258524,0.0003740228,0.0002695394,0.08146714,0.0013103,0.5400122,0.0691964,0.3026871],"study_design_scores_gemma":[0.00001607069,0.00002961685,0.001562449,0.0003040127,0.00004710932,0.000177215,0.00008251511,0.3048855,0.000562602,0.6294649,0.06280713,0.00006076338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00074938,0.005465948,0.9858987,0.001935607,0.0003925201,0.0001316254,0.001052355,0.000949575,0.003424294],"genre_scores_gemma":[0.06246075,0.01367632,0.9096678,0.0008776018,0.001835627,0.001485228,0.003960827,0.0007940329,0.005241835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01148774,"threshold_uncertainty_score":0.03843033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3765235053204907,"score_gpt":0.4540380575911145,"score_spread":0.07751455227062387,"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."}}