{"id":"W4321351204","doi":"10.1002/sim.9685","title":"Impute‐then‐exclude versus exclude‐then‐impute: Lessons when imputing a variable used both in cohort creation and as an independent variable in the analysis model","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Missing data; Imputation (statistics); Statistics; Sample size determination; Variable (mathematics); Random variable; Computer science; Mathematics; Medicine; Econometrics","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":[],"consensus_categories":[],"category_scores_codex":[0.006749697,0.0003299466,0.0008794083,0.0007744321,0.0001298936,0.00008197974,0.0004335804,0.0002019304,0.0001725065],"category_scores_gemma":[0.00731872,0.000237325,0.00002988527,0.001977585,0.0002123608,0.0001370278,0.0001572026,0.0005523817,0.000004733088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002074761,"about_ca_system_score_gemma":0.0002156583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002495173,"about_ca_topic_score_gemma":0.001363261,"domain_scores_codex":[0.9960649,0.0007577335,0.001021531,0.000667986,0.0008254889,0.0006623807],"domain_scores_gemma":[0.9892219,0.009631381,0.0002613084,0.000616184,0.0001128308,0.0001563584],"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":[0.0001273413,0.0001522704,0.01178931,0.0001173737,0.0001326085,0.0001439853,0.008429614,0.0009851122,0.0001200682,0.9667372,0.0006394425,0.01062568],"study_design_scores_gemma":[0.00162667,0.0001428014,0.01746139,0.0001615907,0.0002621097,0.000004626958,0.0009165503,0.3650456,0.00000256491,0.6141801,0.00001817137,0.0001778708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02283255,0.0000304746,0.9735207,0.0005566003,0.0001620934,0.0005832572,0.0002596896,0.00005997959,0.00199464],"genre_scores_gemma":[0.223123,0.0001292222,0.7760537,0.0001756594,0.0001192235,0.0001067409,0.0001383606,0.00004353066,0.0001105216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3640605,"threshold_uncertainty_score":0.9677833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09486507976885547,"score_gpt":0.4341099087394667,"score_spread":0.3392448289706113,"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."}}