{"id":"W2604999944","doi":"10.1002/cjs.11316","title":"Big data and partial least‐squares prediction","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Partial least squares regression; Statistics; Mathematics; Regression; Context (archaeology); Regression analysis; Dimension (graph theory); Linear regression; Sample (material); Sample size determination; Econometrics; Combinatorics; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.02007919,0.0007986379,0.001189666,0.001298064,0.002281115,0.004546597,0.00232301,0.004667873,0.005631624],"category_scores_gemma":[0.08674578,0.0005054079,0.0008560095,0.002662619,0.01098983,0.004502238,0.002620799,0.01147415,0.001321004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007404798,"about_ca_system_score_gemma":0.008098007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06656811,"about_ca_topic_score_gemma":0.06240557,"domain_scores_codex":[0.986241,0.008817686,0.0004246282,0.00123693,0.002914399,0.0003653053],"domain_scores_gemma":[0.9257427,0.05620328,0.002329197,0.004947375,0.009587838,0.001189653],"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":[0.0000453002,0.000007385484,0.000763893,0.0001686013,0.00005241742,0.00009358711,0.0002668361,0.007258969,0.00009170541,0.8520336,0.1183429,0.02087488],"study_design_scores_gemma":[0.00001791938,0.00001424891,0.001005769,0.0004033308,0.0000182263,0.0000541218,0.0001500735,0.02418807,0.0002635638,0.8547049,0.1191183,0.00006148274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.004952565,0.03626973,0.3053081,0.6070282,0.01654036,0.00006572634,0.001674155,0.0004574697,0.02770355],"genre_scores_gemma":[0.55489,0.03565678,0.1681327,0.1643573,0.03954132,0.0005589404,0.001419268,0.001295812,0.03414788],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.06656811,"threshold_uncertainty_score":0.1323613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3057253991635092,"score_gpt":0.3756009962035586,"score_spread":0.06987559704004942,"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."}}