{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026464,0.0001803135,0.0005080158,0.0002006988,0.0001817413,0.00005579329,0.0002124695,0.00004539943,0.00001670206],"category_scores_gemma":[0.01419621,0.0001465826,0.0000869624,0.0002625826,0.00006730236,0.00009645125,0.00004243197,0.0003642546,0.000007488743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002682273,"about_ca_system_score_gemma":0.0003063402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000312685,"about_ca_topic_score_gemma":0.0000106496,"domain_scores_codex":[0.997659,0.00009227701,0.00102046,0.0001664018,0.0004234304,0.0006384213],"domain_scores_gemma":[0.9922836,0.006180776,0.0007368986,0.0001439397,0.0005693568,0.00008547297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006560457,0.00008809762,0.00002837668,0.0002734477,0.0001122761,0.00001473578,0.0003051751,0.0001626474,0.000702003,0.8011594,0.0006777699,0.1964105],"study_design_scores_gemma":[0.001630733,0.0009407446,0.00002291713,0.00008230456,0.0002099971,0.00004373927,0.0004355047,0.053888,0.0004934404,0.9420249,0.00006208082,0.0001656519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004024291,0.0003072788,0.9946985,0.0001059451,0.0004138531,0.0002463977,0.0001405378,0.00004444891,0.00001870017],"genre_scores_gemma":[0.1026582,0.0001146001,0.8969138,0.00002563724,0.0001575793,0.00001291509,0.000006469606,0.00003304785,0.00007779222],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1962448,"threshold_uncertainty_score":0.9941077,"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."}}