{"id":"W4414159953","doi":"10.1016/j.sste.2025.100742","title":"Variable Screening Methods in Conditional Logistic Individual Level Models of Disease Spread","year":2025,"lang":"en","type":"article","venue":"Spatial and Spatio-temporal Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Calgary","keywords":"Overfitting; Akaike information criterion; Feature selection; Logistic regression; Information Criteria; Variable (mathematics); Selection (genetic algorithm)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00362967,0.0002133947,0.0008984845,0.0002088001,0.00007805977,0.000009523632,0.0001786352,0.000188943,0.0001818867],"category_scores_gemma":[0.01526532,0.000183524,0.00006872217,0.0002312103,0.000392649,0.00009141358,0.0001567181,0.0002700757,8.558632e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002320196,"about_ca_system_score_gemma":0.0001804074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003200318,"about_ca_topic_score_gemma":0.0003207274,"domain_scores_codex":[0.996325,0.001739136,0.001060264,0.0004120863,0.000119026,0.000344446],"domain_scores_gemma":[0.9868022,0.01238388,0.0003328046,0.0002282347,0.0001103485,0.000142512],"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":[0.0001698093,0.00008287934,0.07889758,0.0002000768,0.00004323924,0.000004196886,0.00004071041,0.0002585037,0.00001500302,0.8896196,0.0003595369,0.03030884],"study_design_scores_gemma":[0.0004618471,0.0000750973,0.07374564,0.0001334127,0.00006411563,0.000001098289,0.00001697625,0.09873397,0.00002417207,0.826524,0.00008002332,0.000139693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002255908,0.0001805982,0.9950714,0.0006150718,0.000135902,0.00027236,0.00055049,0.00002515502,0.0008931201],"genre_scores_gemma":[0.2854429,0.00001058931,0.7139487,0.0003082343,0.00003419464,0.0000399491,0.0001511924,0.000007825851,0.00005636647],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.283187,"threshold_uncertainty_score":0.9930295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3241750693430864,"score_gpt":0.4696500327162242,"score_spread":0.1454749633731378,"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."}}