{"id":"W4362648691","doi":"10.1214/23-ejs2124","title":"Improving estimation efficiency for two-phase, outcome-dependent sampling studies","year":2023,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Statistics; Mathematics; Outcome (game theory); Sampling (signal processing); Selection (genetic algorithm); Sample size determination; Econometrics; Conditional probability distribution; Data mining; Computer 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05250739,0.001136742,0.002014211,0.001860173,0.0005380002,0.001479429,0.002198557,0.001286247,0.003334131],"category_scores_gemma":[0.1650196,0.0008237927,0.001440928,0.002445269,0.001046781,0.001929407,0.002806733,0.002115387,0.0007026658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008181253,"about_ca_system_score_gemma":0.002467579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002551541,"about_ca_topic_score_gemma":0.003092726,"domain_scores_codex":[0.9698135,0.02667769,0.0008797012,0.001181276,0.001237735,0.0002102063],"domain_scores_gemma":[0.8705947,0.1169407,0.003189595,0.005654601,0.003132219,0.000488278],"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":[0.001384141,0.0004082972,0.03140582,0.001766018,0.001292453,0.0005990943,0.0009069724,0.1864099,0.005302337,0.1542416,0.007395518,0.6088879],"study_design_scores_gemma":[0.0003764596,0.0003191186,0.003707276,0.0001796075,0.0002237975,0.0002678921,0.0001330977,0.890532,0.001780541,0.09485344,0.007572743,0.00005407657],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004313403,0.0003570422,0.994387,0.000231832,0.00002901065,0.0001548059,0.00006155264,0.0001449924,0.0003203758],"genre_scores_gemma":[0.09267519,0.0005039363,0.9046333,0.0002846081,0.00008793512,0.0006708893,0.0003351124,0.0001064956,0.0007024459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05250739,"threshold_uncertainty_score":0.2776889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1233054509736014,"score_gpt":0.4787470123097977,"score_spread":0.3554415613361962,"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."}}