{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0479086,0.0003986489,0.002165283,0.0007009712,0.00009850579,0.0002021955,0.0002036394,0.0005100399,0.00002688904],"category_scores_gemma":[0.1171794,0.0003488885,0.00007070966,0.0004250402,0.0002281131,0.000103603,0.000353991,0.002087099,6.589477e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008679569,"about_ca_system_score_gemma":0.0004633757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001264755,"about_ca_topic_score_gemma":0.001526939,"domain_scores_codex":[0.9461686,0.05052046,0.001997486,0.000558166,0.0003584255,0.0003968604],"domain_scores_gemma":[0.9384155,0.05849574,0.001740362,0.000191342,0.0008896432,0.0002674529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000326029,0.0004874617,0.4992903,0.001804049,0.0003194602,0.0002523015,0.003078422,0.0008487657,0.000504414,0.003587944,0.00007635503,0.4894245],"study_design_scores_gemma":[0.0006599432,0.0005555781,0.4660023,0.0002594986,0.0002565804,0.0003377649,0.0004345798,0.1301763,0.0000866156,0.4008265,0.00000884672,0.0003955605],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.160035,0.001674911,0.837434,0.0000330233,0.0004343269,0.0001730224,0.0002038841,0.000007830613,0.000003945742],"genre_scores_gemma":[0.05015587,0.0008400839,0.9487761,0.0000426537,0.00007825676,0.000003276771,0.00005561064,0.00004476936,0.000003329933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4890289,"threshold_uncertainty_score":0.9998963,"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."}}