{"id":"W4408047762","doi":"10.1007/s42081-025-00298-x","title":"Application of machine learning methods in the imputation of heterogeneous co-missing data","year":2025,"lang":"en","type":"article","venue":"Japanese Journal of Statistics and Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact","funders":"Canadian Institutes of Health Research; McLaughlin Centre, University of Toronto","keywords":"Imputation (statistics); Missing data; Computer science; Machine learning; Artificial intelligence; Data mining","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":[0.02806741,0.001122197,0.003168865,0.003492759,0.001658027,0.002343907,0.004461805,0.002665721,0.001907675],"category_scores_gemma":[0.067368,0.001442299,0.003457924,0.004813095,0.00141265,0.00294932,0.003504144,0.004201591,0.0005077778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008753759,"about_ca_system_score_gemma":0.003015134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004172588,"about_ca_topic_score_gemma":0.003681507,"domain_scores_codex":[0.9856114,0.01066587,0.0006743175,0.001765849,0.0009780284,0.0003045335],"domain_scores_gemma":[0.9355209,0.0548122,0.00227017,0.004473477,0.002416698,0.0005065834],"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":[0.000525761,0.000412528,0.01880992,0.0006174088,0.001834611,0.0005299695,0.000630206,0.58246,0.001250693,0.09638571,0.003770595,0.2927726],"study_design_scores_gemma":[0.00003346376,0.0000305238,0.0009595833,0.00005758416,0.00009269107,0.0001195341,0.00003597066,0.9381368,0.0004254449,0.05906911,0.0009998013,0.00003960344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004628391,0.0003919858,0.9944518,0.0001742239,0.00004634793,0.00002385323,0.00005464789,0.00008871395,0.0001399292],"genre_scores_gemma":[0.2027976,0.0009734678,0.7934549,0.0002267532,0.0003120004,0.0002783393,0.0007610398,0.0001477992,0.001048047],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02806741,"threshold_uncertainty_score":0.1484364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04797112399033372,"score_gpt":0.4199266282748576,"score_spread":0.3719555042845239,"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."}}