{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06566882,0.002245168,0.003322392,0.002776232,0.001312459,0.001866893,0.003163784,0.002939113,0.00377412],"category_scores_gemma":[0.1755938,0.001374043,0.00333675,0.002543631,0.00437177,0.003914435,0.004568646,0.004572017,0.0007564829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001481127,"about_ca_system_score_gemma":0.004832913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004173842,"about_ca_topic_score_gemma":0.003486125,"domain_scores_codex":[0.9758025,0.01722206,0.001080585,0.00224113,0.002989612,0.0006641273],"domain_scores_gemma":[0.8096511,0.163744,0.006561569,0.01001657,0.008625243,0.001401505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006526946,0.0002539938,0.01600109,0.0006247319,0.0009777435,0.0009942523,0.0006115517,0.637904,0.005239834,0.2442327,0.003716073,0.08879123],"study_design_scores_gemma":[0.00008165109,0.0001700512,0.001319283,0.00008951026,0.00007822598,0.0001431534,0.0000380313,0.9079932,0.001719872,0.08761102,0.000723911,0.0000320289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01345608,0.0004763153,0.9842888,0.0004859892,0.0000360465,0.00008562044,0.0001047754,0.0002755095,0.0007909279],"genre_scores_gemma":[0.5306586,0.001232831,0.4594181,0.00103431,0.0003541046,0.001407899,0.001488374,0.0006379715,0.003767656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06566882,"threshold_uncertainty_score":0.3472941,"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."}}