{"id":"W3198343911","doi":"10.1002/cjs.11772","title":"Optimal multiwave validation of secondary use data with outcome and exposure misclassification","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute; University of North Carolina at Chapel Hill; National Institutes of Health; Vanderbilt University; Patient-Centered Outcomes Research Institute","keywords":"Estimator; Computer science; Variance (accounting); Outcome (game theory); Optimal design; Observational study; Data mining; Mathematical optimization; Grid; Resource (disambiguation); Machine learning; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.04978669,0.0008192061,0.001731604,0.0008283716,0.0006604654,0.001225545,0.001839859,0.001826202,0.002452634],"category_scores_gemma":[0.123751,0.0009538066,0.001363451,0.0009165062,0.002029709,0.001597883,0.002787854,0.001677607,0.0004967076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008661518,"about_ca_system_score_gemma":0.002315861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001173776,"about_ca_topic_score_gemma":0.0009220827,"domain_scores_codex":[0.9551377,0.03951273,0.0009418683,0.002240547,0.001617755,0.0005494385],"domain_scores_gemma":[0.8770315,0.0986953,0.007856169,0.01118293,0.004434847,0.0007993465],"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":[0.003188954,0.0008614812,0.03324777,0.0005521436,0.0004927211,0.0002369124,0.000483926,0.5792547,0.006418935,0.1318599,0.002072053,0.2413305],"study_design_scores_gemma":[0.000818887,0.001115873,0.006166882,0.0001274027,0.0001069176,0.0001049078,0.00007928285,0.865721,0.00432368,0.1196547,0.001722065,0.00005843331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02833111,0.0001097429,0.9701641,0.0002839251,0.00002848837,0.0003265562,0.0001112553,0.0001022843,0.0005425743],"genre_scores_gemma":[0.5322186,0.0001435809,0.4646649,0.0002809165,0.00003788895,0.001404744,0.0003329048,0.0000423593,0.0008740777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04978669,"threshold_uncertainty_score":0.2633003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3119308867935993,"score_gpt":0.3904439519980124,"score_spread":0.07851306520441315,"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."}}