{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008720945,0.000230669,0.0005885708,0.00004647943,0.00009352043,0.0003810259,0.0003928335,0.0001606578,0.00005470838],"category_scores_gemma":[0.02545434,0.0001888812,0.00006105634,0.00007024552,0.00002442202,0.00007029808,0.001481843,0.000165693,0.000001667054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005591517,"about_ca_system_score_gemma":0.0001325341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009612239,"about_ca_topic_score_gemma":0.00001841476,"domain_scores_codex":[0.9984245,0.0001541131,0.0003358741,0.0006730447,0.0002033374,0.0002091363],"domain_scores_gemma":[0.993054,0.004987601,0.0001501463,0.001214764,0.0005041353,0.0000893853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006537599,0.0001506812,0.00001511195,0.004798526,0.0007958577,0.00002050719,0.001430369,0.0009800016,0.0009748368,0.5676299,0.06975076,0.3533881],"study_design_scores_gemma":[0.0001504483,0.00002762765,0.000009054669,0.0003922855,0.0002021478,4.746807e-7,0.0002813386,0.1916712,0.0006572754,0.8028031,0.003468943,0.0003360603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003422972,0.0001721581,0.9943129,0.001610581,0.002271156,0.0006564963,0.0003797493,0.00008223871,0.0001723701],"genre_scores_gemma":[0.003701404,0.00002195977,0.9939616,0.0001545602,0.001247996,0.00006187348,0.0001801139,0.00003420396,0.0006363284],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.353052,"threshold_uncertainty_score":0.9827546,"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."}}