{"id":"W3179091049","doi":"10.31234/osf.io/rq6yb","title":"Tutorial: How to Generate Missing Data For Simulation Studies","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Missing data; Computer science; Data mining; Data science; Machine learning","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":[0.009989675,0.003254338,0.001926353,0.002717344,0.0007617899,0.002997455,0.002828083,0.003080109,0.108484],"category_scores_gemma":[0.06875793,0.001995103,0.003052286,0.002642194,0.0008594844,0.005083468,0.002106127,0.00611277,0.04012607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027372,"about_ca_system_score_gemma":0.001828252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001275041,"about_ca_topic_score_gemma":0.00215213,"domain_scores_codex":[0.9950778,0.003147832,0.0004348306,0.0003222195,0.0009149805,0.0001022133],"domain_scores_gemma":[0.9562868,0.03676692,0.000929997,0.001639783,0.003730415,0.0006461546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001943065,0.0002658126,0.0008180571,0.003951113,0.0003202094,0.0006861895,0.0004460978,0.02440415,0.00201834,0.1353323,0.433014,0.3985495],"study_design_scores_gemma":[0.0002180338,0.00009600032,0.0005219096,0.001195829,0.0001199143,0.00102624,0.000110695,0.06023925,0.002189277,0.3316241,0.6025001,0.0001586634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002806335,0.002226585,0.9781449,0.002834356,0.0012836,0.0003290404,0.001689664,0.00614407,0.007067116],"genre_scores_gemma":[0.004651013,0.004475119,0.9693634,0.001894677,0.001229413,0.001199363,0.002093236,0.003394185,0.01169964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.108484,"threshold_uncertainty_score":0.362915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5334281666007765,"score_gpt":0.5366739157454582,"score_spread":0.003245749144681676,"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."}}