{"id":"W4253069444","doi":"10.21203/rs.3.rs-422960/v1","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":"preprint","venue":"Research Square","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Imputation (statistics); Missing data; Pandemic; Coronavirus disease 2019 (COVID-19); Democracy; Geography; Statistics; Data mining; Political science; Computer science; Medicine; Mathematics; Infectious disease (medical specialty); Politics","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":[],"consensus_categories":[],"category_scores_codex":[0.06168855,0.0008318314,0.00113515,0.001417566,0.0009260191,0.001614612,0.002666265,0.001522618,0.001064666],"category_scores_gemma":[0.1080832,0.0004157206,0.001695638,0.002804895,0.000635803,0.001475483,0.001312096,0.001632827,0.0002617367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094905,"about_ca_system_score_gemma":0.002519979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01694485,"about_ca_topic_score_gemma":0.01060348,"domain_scores_codex":[0.9748207,0.02123339,0.001194027,0.001118938,0.0012529,0.0003799861],"domain_scores_gemma":[0.8265938,0.1545915,0.00464096,0.005054757,0.008135791,0.0009833883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.004525464,0.002283666,0.2175521,0.001946974,0.003893998,0.0005581965,0.003306738,0.4756684,0.002319983,0.005675631,0.007941673,0.2743271],"study_design_scores_gemma":[0.0003595685,0.001381012,0.04298241,0.0004523712,0.0004926961,0.0001322816,0.001333283,0.9443443,0.003124244,0.002509878,0.002778581,0.0001092166],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8530769,0.00140495,0.1370028,0.001821823,0.0002101975,0.0005976618,0.002263449,0.001360832,0.00226142],"genre_scores_gemma":[0.8671153,0.0004860326,0.1292844,0.0002168593,0.00005129565,0.00039556,0.001964176,0.0001062049,0.0003803247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06168855,"threshold_uncertainty_score":0.3262441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8903758142698626,"score_gpt":0.6736066004780074,"score_spread":0.2167692137918552,"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."}}