{"id":"W4386021106","doi":"10.1002/cjs.11793","title":"High‐dimensional variable selection accounting for heterogeneity in regression coefficients across multiple data sources","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute; Agency for Healthcare Research and Quality","keywords":"Lasso (programming language); Pairwise comparison; Estimator; Oracle; Regression; Cluster analysis; Linear regression; Computer science; Feature selection; Variable (mathematics); Regression analysis; Penalty method; Selection (genetic algorithm); Statistics; Data mining; Mathematics; Algorithm; Econometrics; Mathematical optimization; Artificial intelligence","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":[0.04767733,0.00195465,0.003044881,0.002650376,0.001265561,0.002705964,0.003084817,0.001585844,0.001599936],"category_scores_gemma":[0.06935611,0.0009970735,0.003664316,0.005293495,0.001730159,0.001924938,0.003300644,0.00261373,0.0003992669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009621841,"about_ca_system_score_gemma":0.002857204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001978921,"about_ca_topic_score_gemma":0.002025885,"domain_scores_codex":[0.9617062,0.02918398,0.001879454,0.003845225,0.00274627,0.0006388507],"domain_scores_gemma":[0.935163,0.04777762,0.00594411,0.007718413,0.002879264,0.0005174591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008711609,0.0005208576,0.1031584,0.00205862,0.006787397,0.001494589,0.001199533,0.3830707,0.008268363,0.1027163,0.01090101,0.378953],"study_design_scores_gemma":[0.000231054,0.0002854897,0.02036984,0.000237663,0.0008937773,0.0004816204,0.0002883168,0.8270022,0.003303155,0.1410135,0.005759189,0.0001342769],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02402618,0.0009156567,0.9730451,0.0006793819,0.00007683894,0.0001906543,0.0003176343,0.0002190445,0.000529511],"genre_scores_gemma":[0.5379626,0.0008509615,0.4551563,0.0006952998,0.0004186838,0.001423053,0.002036613,0.0001613753,0.001295034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04767733,"threshold_uncertainty_score":0.2521448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1596500559881475,"score_gpt":0.3869226391123616,"score_spread":0.2272725831242141,"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."}}