{"id":"W4410471507","doi":"10.31234/osf.io/rq6yb_v1","title":"Tutorial: How to Generate Missing Data For Simulation Studies","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Missing data; Computer science; 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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002590286,0.0002178161,0.000485919,0.0002133528,0.0002659103,0.001676023,0.001590464,0.0001885047,0.0001073734],"category_scores_gemma":[0.0100518,0.000169641,0.0001292377,0.0004698339,0.0000307728,0.0002878075,0.003036478,0.000137684,0.00001744162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006908741,"about_ca_system_score_gemma":0.000183953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001857024,"about_ca_topic_score_gemma":0.00003310299,"domain_scores_codex":[0.9968451,0.0001074634,0.0006813467,0.001360842,0.0008160078,0.0001892318],"domain_scores_gemma":[0.991253,0.002884193,0.0003465181,0.003325434,0.002078784,0.0001121157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002162994,0.00006336204,0.00009844571,0.00004392451,0.0001161761,0.000001123933,0.0006693468,0.4679818,0.001097225,0.004701226,0.302898,0.2223078],"study_design_scores_gemma":[0.0001060516,0.00001261003,0.00007175315,0.00003993356,0.00003454286,2.150343e-7,0.000671591,0.6262133,0.001472371,0.03308474,0.3380339,0.0002589255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006162125,0.0003503632,0.9775397,0.01242016,0.001478608,0.001260706,0.000284839,0.0001976944,0.0003057938],"genre_scores_gemma":[0.5832957,0.00004072299,0.4026515,0.0009109434,0.001743311,0.0002779125,0.00074855,0.00003432801,0.01029702],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5771336,"threshold_uncertainty_score":0.9993603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6986255797806713,"score_gpt":0.5893709231828437,"score_spread":0.1092546565978276,"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."}}