{"id":"W3041151490","doi":"10.1093/jssam/smab004","title":"Imputation Procedures in Surveys Using Nonparametric and Machine Learning Methods: An Empirical Comparison","year":2021,"lang":"en","type":"preprint","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Imputation (statistics); Nonparametric statistics; Computer science; Machine learning; Artificial intelligence; Data mining; Data set; Econometrics; Missing data; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.1388914,0.0005960376,0.00134219,0.003456406,0.0007205585,0.002412758,0.001953996,0.001758024,0.003077113],"category_scores_gemma":[0.3922183,0.0004911525,0.001722077,0.006594833,0.002534029,0.004810079,0.002519685,0.002149339,0.0004633788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001120763,"about_ca_system_score_gemma":0.001582771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001399302,"about_ca_topic_score_gemma":0.001115916,"domain_scores_codex":[0.8072861,0.1783908,0.002652236,0.002510478,0.008475523,0.0006849077],"domain_scores_gemma":[0.3414253,0.6034805,0.01871352,0.02414095,0.01141555,0.0008241487],"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":[0.002449241,0.001171407,0.1539497,0.002534267,0.003943099,0.0002143285,0.002762455,0.1226231,0.0004608427,0.1834532,0.009550793,0.5168876],"study_design_scores_gemma":[0.0007252959,0.002420154,0.1894022,0.002608278,0.001273051,0.001099207,0.003297981,0.5156788,0.001814469,0.2623169,0.01902459,0.0003392057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3292924,0.01711799,0.6415478,0.002442937,0.0002213683,0.0005806891,0.0007020584,0.0003601213,0.007734559],"genre_scores_gemma":[0.8537108,0.002898018,0.1408037,0.0003379005,0.0001874051,0.0004079714,0.0007185184,0.0001320023,0.0008036966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1388914,"threshold_uncertainty_score":0.7345369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5742043220523099,"score_gpt":0.5636730961020205,"score_spread":0.01053122595028932,"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."}}