{"id":"W2953859485","doi":"10.1002/cjs.11513","title":"Synthetic data method to incorporate external information into a current study","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Imputation (statistics); Missing data; Statistics; Context (archaeology); Computer science; Data set; Regression; Regression analysis; Data mining; Set (abstract data type); Mathematics; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002066636,0.0001704055,0.0004124813,0.0003731879,0.00008646762,0.0002093295,0.0007597327,0.00004200133,0.0005076578],"category_scores_gemma":[0.004241936,0.0001465713,0.00002773986,0.0002520978,0.00003902069,0.0004391065,0.00008429674,0.0003485945,0.0001395458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001633705,"about_ca_system_score_gemma":0.001201787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00144953,"about_ca_topic_score_gemma":0.003347313,"domain_scores_codex":[0.9979612,0.0003021079,0.000878221,0.0001671814,0.0003961132,0.0002951841],"domain_scores_gemma":[0.9963679,0.001099517,0.0005160005,0.000581488,0.0006249935,0.0008101367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004274607,0.0000800581,0.005819788,0.0001947135,0.00006158908,0.0001322518,0.003075648,0.00001395526,0.000023279,0.2856875,0.0126976,0.6921709],"study_design_scores_gemma":[0.0007130159,0.0008507986,0.007266617,0.0003692333,0.0001869588,0.0001218096,0.001106474,0.005245457,0.00002318854,0.9719433,0.01182902,0.0003441778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004305388,0.00004002239,0.9932244,0.00009339656,0.0008135241,0.0003798569,0.0009101888,0.000005434209,0.0002278211],"genre_scores_gemma":[0.07961891,0.000003195947,0.9201421,0.0001061174,0.00008470772,0.000002765301,0.00001054018,0.00001577091,0.0000159491],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6918267,"threshold_uncertainty_score":0.5977003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08839897051169125,"score_gpt":0.3934734528448364,"score_spread":0.3050744823331452,"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."}}