{"id":"W4404731945","doi":"10.1101/2024.11.25.24317882","title":"Variable selection for competing risk regression models: recommendations for analyzing data from epidemiological studies","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Epidemiology; Regression analysis; Selection (genetic algorithm); Computer science; Model selection; Regression; Variable (mathematics); Econometrics; Data science; Statistics; Medicine; Artificial intelligence; Mathematics; Machine learning","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":[0.005973849,0.0003171021,0.0009358916,0.00008570529,0.0003154646,0.00008127317,0.0005152794,0.0002941749,0.0000599649],"category_scores_gemma":[0.05725481,0.0002233291,0.0001398204,0.0001320584,0.00005507754,0.00005719688,0.001680887,0.0007863077,0.000004024542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008990096,"about_ca_system_score_gemma":0.0000785305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001070663,"about_ca_topic_score_gemma":0.00003471072,"domain_scores_codex":[0.996953,0.0007230252,0.0008817539,0.001007732,0.0001256554,0.0003088972],"domain_scores_gemma":[0.9639247,0.034402,0.0005501359,0.0007361173,0.0003166296,0.00007040605],"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":[0.0001259812,0.0001724496,0.00251601,0.002864329,0.001446565,8.843029e-7,0.0007281305,0.001278794,0.0001935124,0.8790583,0.06932862,0.04228645],"study_design_scores_gemma":[0.00008442614,0.00002622272,0.00001639124,0.0008620539,0.0004147619,2.568402e-7,0.0001053379,0.4460903,0.00002667541,0.5512757,0.0009605236,0.0001373463],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005019816,0.00140066,0.9846404,0.001114303,0.001178914,0.0008765565,0.005442218,0.0001838403,0.0001433598],"genre_scores_gemma":[0.00469632,0.0005643726,0.9925969,0.00005192566,0.0005680836,0.000508079,0.0008811319,0.00004554507,0.00008769688],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4448115,"threshold_uncertainty_score":0.9506863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5873837685078472,"score_gpt":0.5240360866104358,"score_spread":0.06334768189741147,"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."}}