{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001756549,0.0001240919,0.0002945465,0.0001771095,0.0002554812,0.00009029912,0.0003163461,0.00008386443,0.0000468148],"category_scores_gemma":[0.01303009,0.000108097,0.00002272813,0.0003760017,0.00006964153,0.0001141249,0.00005271498,0.000218907,0.000004880028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189449,"about_ca_system_score_gemma":0.0006815287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001822976,"about_ca_topic_score_gemma":0.01332386,"domain_scores_codex":[0.9984787,0.00009406657,0.0005625441,0.0001877061,0.0002317044,0.0004452428],"domain_scores_gemma":[0.9961665,0.002630552,0.000327934,0.0001881039,0.0004115343,0.0002754274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005430862,0.0003895314,0.2525648,0.001506806,0.000369642,0.0006754196,0.003017928,0.01750666,0.003295254,0.2550951,0.2515018,0.213534],"study_design_scores_gemma":[0.003253114,0.0004146498,0.05756302,0.0009833039,0.0001259814,0.0001246231,0.0004976989,0.5275717,0.001132766,0.4004533,0.007249957,0.0006298675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3131578,0.00002270816,0.6818856,0.00004431054,0.0005446908,0.0001303479,0.004199384,0.000008770289,0.000006337958],"genre_scores_gemma":[0.3187769,0.000003369797,0.6808689,0.00005174284,0.0001235992,0.00000299673,0.000105395,0.00002225277,0.00004479091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5100651,"threshold_uncertainty_score":0.9952836,"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."}}