{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005738508,0.00008747171,0.0002027835,0.00006967768,0.0003451383,0.0002332859,0.0004384314,0.00004950162,0.0001039072],"category_scores_gemma":[0.01123168,0.00007585605,0.00001273145,0.0000190536,0.0002707561,0.0001312876,0.00004533781,0.0001892421,0.000002964116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002925668,"about_ca_system_score_gemma":0.0005637536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001295643,"about_ca_topic_score_gemma":0.00675264,"domain_scores_codex":[0.9991335,0.00005715628,0.0003464518,0.0001115701,0.0001531842,0.0001981888],"domain_scores_gemma":[0.9979295,0.0004972671,0.0003557576,0.0004761317,0.0002112035,0.0005302068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002233024,0.00001847606,0.02171126,0.0000995583,0.00007540097,0.0003928728,0.00039676,0.000001070424,0.00002691311,0.4485675,0.07163677,0.4570511],"study_design_scores_gemma":[0.0008743335,0.0004244715,0.09930369,0.000265865,0.0002692357,0.0003176965,0.0002768464,0.009721164,0.00005754314,0.8430859,0.04513207,0.0002711336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009289484,0.0001190251,0.9827152,0.0003718241,0.001254603,0.00006152257,0.005233652,0.000003517432,0.0009511909],"genre_scores_gemma":[0.6004635,0.00005469857,0.3986615,0.00004911458,0.0006505139,5.866513e-7,0.00001136273,0.00001572674,0.0000930346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.591174,"threshold_uncertainty_score":0.9970971,"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."}}