{"id":"W3157805359","doi":"10.1186/s12963-021-00274-z","title":"Addressing missing values in routine health information system data: an evaluation of imputation methods using data from the Democratic Republic of the Congo during the COVID-19 pandemic","year":2021,"lang":"en","type":"article","venue":"Population Health Metrics","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Missing data; Imputation (statistics); Statistics; Data quality; Wilcoxon signed-rank test; Econometrics; Medicine; Data mining; Computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2329139,0.0001053111,0.0003461053,0.0002597522,0.00156798,0.0000948528,0.0007528909,0.000123188,0.00001067744],"category_scores_gemma":[0.1661328,0.00007090656,0.00003300191,0.003209101,0.0001369292,0.001394573,0.0002440667,0.0002627172,1.805141e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128414,"about_ca_system_score_gemma":0.004505161,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05193215,"about_ca_topic_score_gemma":0.009675417,"domain_scores_codex":[0.785197,0.2089351,0.00266613,0.0006172322,0.002054909,0.0005296933],"domain_scores_gemma":[0.9728353,0.02236676,0.002505132,0.001551439,0.0006036675,0.0001377153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000213828,0.00004139479,0.8689218,0.0003564622,0.00003329191,1.708995e-7,0.03322544,0.01837525,0.00005867735,0.0004245744,0.00005868808,0.07829048],"study_design_scores_gemma":[0.0003933133,0.00000921988,0.7135425,0.0001054574,0.000043368,0.00000429757,0.01097621,0.2739597,0.00001330238,0.0008358742,0.00006227545,0.00005451954],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8698679,0.002511505,0.1212882,0.004596424,0.0006238396,0.0008972834,0.0001745859,0.00003217846,0.000008031997],"genre_scores_gemma":[0.9668621,0.00009954751,0.03111174,0.0009328747,0.0001058422,0.000005844658,0.0008723117,0.000007833365,0.000001919196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2555844,"threshold_uncertainty_score":0.9997318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8595353331593875,"score_gpt":0.6461316691088818,"score_spread":0.2134036640505057,"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."}}