{"id":"W4387033650","doi":"10.1177/09622802231198795","title":"Logistic regression vs. predictive mean matching for imputing binary covariates","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Missing data; Imputation (statistics); Logistic regression; Statistics; Binary data; Parametric statistics; Covariate; Mathematics; Regression analysis; Multivariate statistics; Matching (statistics); Computer science; Binary number","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":[0.05235824,0.001588444,0.002795894,0.002120198,0.00100753,0.002248733,0.00326497,0.00222008,0.01332096],"category_scores_gemma":[0.1592894,0.001019963,0.004052449,0.004099372,0.001388591,0.003352242,0.003486672,0.004472839,0.003638292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262402,"about_ca_system_score_gemma":0.003503086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003565583,"about_ca_topic_score_gemma":0.003120246,"domain_scores_codex":[0.9536055,0.03427377,0.002402758,0.005426126,0.003383029,0.0009088637],"domain_scores_gemma":[0.9175589,0.06075988,0.005364885,0.01151737,0.004213035,0.0005859397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004061033,0.0004141762,0.04679423,0.002584449,0.00408309,0.0004128937,0.001022353,0.1483801,0.001853923,0.125495,0.03258605,0.6323127],"study_design_scores_gemma":[0.001166286,0.001224807,0.01117687,0.001165932,0.001275677,0.0008150119,0.0001943603,0.7295566,0.006355714,0.2047615,0.04204267,0.0002645134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01379845,0.001530819,0.9762683,0.0007939578,0.0003188878,0.0005744761,0.001607065,0.002602818,0.002505135],"genre_scores_gemma":[0.297784,0.001335695,0.6867305,0.001713244,0.0003333022,0.002933184,0.003805683,0.001468253,0.003896253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05235824,"threshold_uncertainty_score":0.2769002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3427619520314442,"score_gpt":0.6290504285419702,"score_spread":0.286288476510526,"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."}}