{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008524286,0.0009381162,0.001978736,0.0007312918,0.0001628842,0.0001409832,0.001946204,0.000573518,0.005457084],"category_scores_gemma":[0.004920207,0.0008100075,0.0001547338,0.0007165124,0.0005487186,0.00004314223,0.0008271356,0.0005190494,0.0002063911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001176809,"about_ca_system_score_gemma":0.0004268313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004534892,"about_ca_topic_score_gemma":0.004741061,"domain_scores_codex":[0.9947697,0.0003173409,0.001338304,0.001661237,0.0009539903,0.0009594139],"domain_scores_gemma":[0.9912019,0.003317674,0.001191774,0.003267261,0.0005655401,0.0004558531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007636317,0.0005808691,0.0001180712,0.0007393326,0.001868984,0.00002134442,0.00003564477,0.000001024984,0.000008881,0.1753442,0.7825529,0.03865236],"study_design_scores_gemma":[0.0007992956,0.0003927906,0.0002427826,0.0004574609,0.003407223,0.000003143229,0.00004419512,0.01141611,0.000004046462,0.1751967,0.8069326,0.00110374],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00000936482,0.0001664213,0.7197556,0.00003630257,0.0008729874,0.0008144972,0.2573812,0.0002376028,0.02072605],"genre_scores_gemma":[0.00004039318,0.0006832587,0.8217157,0.00009382,0.001549501,0.00008056316,0.03815376,0.0005967605,0.1370863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2192274,"threshold_uncertainty_score":0.9994351,"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."}}