{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042634,0.0007860916,0.001334026,0.003412453,0.0007290606,0.002422097,0.002771793,0.002141819,0.005320844],"category_scores_gemma":[0.1520304,0.000675092,0.001710247,0.00278784,0.001459086,0.002160407,0.002736187,0.002232611,0.0005551243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001251668,"about_ca_system_score_gemma":0.001593542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003066841,"about_ca_topic_score_gemma":0.0023593,"domain_scores_codex":[0.9830216,0.01442352,0.0005137541,0.001126823,0.0007721804,0.0001421843],"domain_scores_gemma":[0.8375254,0.1399585,0.005739464,0.01085653,0.00478756,0.001132497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001003963,0.0004211238,0.05547618,0.0008527702,0.00127719,0.001169218,0.0009611512,0.471916,0.001134827,0.3017387,0.01470531,0.1493436],"study_design_scores_gemma":[0.0001343578,0.0001651132,0.001948264,0.0001695771,0.0001357819,0.0002201515,0.0001229191,0.8451242,0.000425336,0.1428542,0.008652515,0.00004755179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01686318,0.0005405857,0.9786531,0.0009774297,0.0002929027,0.0002233297,0.0009773215,0.0002234057,0.001248798],"genre_scores_gemma":[0.4739228,0.0005290504,0.5164371,0.0009409678,0.0005089175,0.002035941,0.003632116,0.0001864823,0.001806663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.042634,"threshold_uncertainty_score":0.2254728,"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."}}