{"id":"W2119511462","doi":"10.1002/sim.6433","title":"Penalized regression procedures for variable selection in the potential outcomes framework","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; National Cancer Institute; National Institute on Drug Abuse; National Institutes of Health","keywords":"Causal inference; Imputation (statistics); Computer science; Inference; Missing data; Regression; Multivariate statistics; Feature selection; Regression analysis; Artificial intelligence; Model selection; Selection (genetic algorithm); Machine learning; Data mining; Econometrics; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001563287,0.0001476205,0.0003339271,0.0001273708,0.00004491409,0.0000115055,0.0001981871,0.0001121341,0.00004728053],"category_scores_gemma":[0.02207771,0.00008502322,0.000013081,0.0002957458,0.00009346606,0.00006304117,0.00002530819,0.0003268199,0.000001203842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001029148,"about_ca_system_score_gemma":0.0001126315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007234974,"about_ca_topic_score_gemma":0.0001245945,"domain_scores_codex":[0.9986652,0.0001259057,0.000412648,0.0001797715,0.0003821404,0.000234395],"domain_scores_gemma":[0.9974202,0.002023299,0.0001584271,0.0001677115,0.0001852111,0.00004513958],"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":[0.000115702,0.00009160449,0.002127829,0.0001567676,0.000007885732,0.00001191758,0.002164261,0.00003534145,0.0002892188,0.9636171,0.03068065,0.0007017446],"study_design_scores_gemma":[0.0009199322,0.0002519707,0.001227985,0.0004207874,0.00002750988,0.000009243181,0.0007140399,0.001414739,0.00006786412,0.9945011,0.0003463597,0.00009848818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002216272,0.00004729314,0.9951704,0.0008451408,0.0001516555,0.0007578935,0.00002218193,0.00007072654,0.0007184487],"genre_scores_gemma":[0.1199237,0.00002322299,0.8791226,0.0003655579,0.0001277627,0.000183755,0.00002432922,0.00002163244,0.000207364],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1177075,"threshold_uncertainty_score":0.9861597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1177511973363103,"score_gpt":0.4738352817476763,"score_spread":0.356084084411366,"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."}}