{"id":"W4413298197","doi":"10.1177/09622802251362642","title":"Imputation of incomplete ordinal and nominal data by predictive mean matching","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Categorical variable; Missing data; Imputation (statistics); Statistics; Multinomial logistic regression; Mathematics; Ordinal data; Logistic regression; Ordinal regression; Regression analysis; Econometrics; Computer science","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":[0.04089844,0.001188055,0.003191227,0.003098166,0.001139012,0.003002417,0.003972653,0.001757386,0.009889618],"category_scores_gemma":[0.1612747,0.001150189,0.003431233,0.006468124,0.001273631,0.002802102,0.00398198,0.004511255,0.002693892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001411102,"about_ca_system_score_gemma":0.004318797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003364613,"about_ca_topic_score_gemma":0.003063938,"domain_scores_codex":[0.9668032,0.02396112,0.001801736,0.00281154,0.00394222,0.0006802643],"domain_scores_gemma":[0.9139407,0.05935406,0.005395551,0.01423806,0.006513251,0.0005584132],"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":[0.001738222,0.0003426293,0.05116682,0.001933707,0.002207045,0.0008005888,0.001216948,0.1590863,0.002051241,0.1075994,0.02734884,0.6445083],"study_design_scores_gemma":[0.0004182934,0.0003081121,0.008710013,0.0006695148,0.0004854774,0.0006228292,0.0001832546,0.7283694,0.003295367,0.2341628,0.02260173,0.0001733058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00873054,0.0005763416,0.9870288,0.0002964455,0.0001946185,0.0002623906,0.0009346216,0.0008374188,0.001138832],"genre_scores_gemma":[0.1797458,0.0007494167,0.8106193,0.0005897261,0.0002147297,0.001512337,0.004229957,0.0004920385,0.001846654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04089844,"threshold_uncertainty_score":0.2162942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2364490851509043,"score_gpt":0.619632349005499,"score_spread":0.3831832638545947,"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."}}