{"id":"W3202514089","doi":"10.1002/cjs.11635","title":"Model selection properties of forward selection and sequential cross‐validation for high‐dimensional regression","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Intuition; Consistency (knowledge bases); Selection (genetic algorithm); Computer science; Regression; Model selection; Linear regression; Matching (statistics); Mathematical proof; Covariate; Regression analysis; Mathematics; Feature selection; Statistics; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003924118,0.00009711515,0.0002424006,0.0001092375,0.0001525667,0.0000562139,0.00004499852,0.0000782046,0.00005813829],"category_scores_gemma":[0.003141543,0.00008181418,0.00003306347,0.0001005641,0.00008114247,0.0001008779,0.000007503838,0.0001313559,2.401072e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001024073,"about_ca_system_score_gemma":0.001322035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002741334,"about_ca_topic_score_gemma":0.001511396,"domain_scores_codex":[0.9989898,0.00008220996,0.0004727974,0.0001079774,0.0001826837,0.0001644866],"domain_scores_gemma":[0.9975395,0.0002717111,0.0003319641,0.00005099018,0.001600997,0.0002048674],"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":[0.0003103414,0.0000858834,0.002495547,0.001022683,0.000184686,0.00003084662,0.0007572121,0.00447171,0.09355529,0.862137,0.009467827,0.02548094],"study_design_scores_gemma":[0.0008514322,0.0003630236,0.0009031522,0.0003706223,0.0001866955,0.0002015159,0.00006008758,0.1708173,0.1261189,0.6998485,0.00009465955,0.0001841707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2759369,0.00006324385,0.7233675,0.00007092425,0.0001724367,0.00008083713,0.0002901333,0.000002567308,0.00001551715],"genre_scores_gemma":[0.5220677,0.00000744589,0.4777461,0.00001453926,0.00005151089,0.000001936609,0.000007251238,0.000009798345,0.00009371816],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2461308,"threshold_uncertainty_score":0.3760947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1324843204483795,"score_gpt":0.3483088734624338,"score_spread":0.2158245530140543,"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."}}