{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01144594,0.001062579,0.000937508,0.00145716,0.0004580028,0.001180447,0.002514643,0.001221013,0.003507372],"category_scores_gemma":[0.03346429,0.0005555263,0.001781017,0.001550856,0.001542118,0.001578542,0.002046231,0.002571837,0.0005931688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001050257,"about_ca_system_score_gemma":0.001810319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006665922,"about_ca_topic_score_gemma":0.005103337,"domain_scores_codex":[0.9946844,0.004066769,0.0001505916,0.0005153046,0.0004201122,0.0001628567],"domain_scores_gemma":[0.9774156,0.01968364,0.001136122,0.0007374229,0.0008316176,0.000195598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001675571,0.00008977381,0.01063514,0.0003096587,0.0003396177,0.0002307971,0.0003315066,0.6836162,0.000811342,0.1853821,0.004347194,0.113739],"study_design_scores_gemma":[0.00002025991,0.00003907024,0.0007865646,0.00004203679,0.00002518308,0.00004332195,0.00002317992,0.9476863,0.0002465699,0.04967319,0.001393421,0.00002104326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007101303,0.0002345785,0.9912971,0.0003151822,0.00002356675,0.00004996824,0.0001340377,0.000236734,0.0006076366],"genre_scores_gemma":[0.3979253,0.0009573333,0.5932821,0.0005468842,0.0001931318,0.0008868387,0.001220964,0.0002509204,0.004736491],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01144594,"threshold_uncertainty_score":0.06053263,"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."}}