{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04866503,0.0003277476,0.0009266122,0.0006482294,0.0004455985,0.0001095089,0.0008068896,0.0004780886,0.001265004],"category_scores_gemma":[0.3711766,0.0002464591,0.00009998311,0.001807796,0.001171873,0.0000793388,0.0007539204,0.002094712,0.00006444401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002218141,"about_ca_system_score_gemma":0.0005370024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167195,"about_ca_topic_score_gemma":0.00002122374,"domain_scores_codex":[0.9854252,0.008072033,0.001216689,0.001012848,0.002503737,0.001769457],"domain_scores_gemma":[0.7849909,0.2132833,0.0001153566,0.0004754674,0.0004167323,0.0007182531],"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":[0.0003311399,0.0001367114,0.00008317323,0.0005679818,0.00002433638,0.0003192099,0.0004942674,0.000002031184,0.0004133483,0.6767855,0.004554574,0.3162877],"study_design_scores_gemma":[0.0007468029,0.0005415145,0.002835386,0.0008166996,0.0000218435,0.0000106195,0.0006706323,0.1400488,0.0001480298,0.8536108,0.0003176219,0.0002312359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005778818,0.00006206441,0.9938787,0.001628981,0.0004734411,0.0009854945,0.0002344668,0.0002230596,0.001935947],"genre_scores_gemma":[0.01251858,0.0001143235,0.9862471,0.0001045476,0.0003138483,0.0004252698,0.00004536784,0.00007739198,0.0001536071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3225116,"threshold_uncertainty_score":0.9999987,"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."}}