{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08915192,0.0009992527,0.00142505,0.001662228,0.001008618,0.001920838,0.002895046,0.001824774,0.001223998],"category_scores_gemma":[0.1550412,0.0005342514,0.00219499,0.003370544,0.0007126484,0.001831943,0.001716771,0.001589039,0.0002459855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00139697,"about_ca_system_score_gemma":0.003229346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01321857,"about_ca_topic_score_gemma":0.00941705,"domain_scores_codex":[0.9559622,0.03759649,0.002061557,0.001685371,0.002159865,0.0005345232],"domain_scores_gemma":[0.7530594,0.2214645,0.007198229,0.006519566,0.01053678,0.001221423],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006602117,0.002592434,0.1922166,0.003550602,0.00480543,0.0006302662,0.00571036,0.3631611,0.001992203,0.006897879,0.006107669,0.4057333],"study_design_scores_gemma":[0.000901169,0.003261618,0.06317721,0.001074861,0.001176105,0.0002727318,0.002116696,0.9149699,0.003479258,0.004671843,0.004695373,0.000203126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7744969,0.002600087,0.2128606,0.002051166,0.0002341333,0.001419299,0.002174568,0.001214754,0.002948593],"genre_scores_gemma":[0.7813294,0.00110321,0.213909,0.0002568495,0.00006495597,0.0009635572,0.001831986,0.0001332168,0.0004078554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9108481,"threshold_uncertainty_score":0.471486,"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."}}