{"id":"W2064228679","doi":"10.1198/016214506000000258","title":"Statistical Inference for the Difference Between the Best Treatment Mean and a Control Mean","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Confidence interval; Mathematics; Mean difference; Inference; Upper and lower bounds; Homogeneous; Statistics; Coverage probability; Mathematical optimization; Computer science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.000917814,0.0001918231,0.0005166217,0.00003264433,0.0002983831,0.0001015774,0.0003155944,0.00004491509,0.0000081213],"category_scores_gemma":[0.004485923,0.00008410919,0.0001024262,0.0001457303,0.0003908814,0.0000703354,0.00004489482,0.000298022,0.000001444629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005038359,"about_ca_system_score_gemma":0.00009486824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003216727,"about_ca_topic_score_gemma":0.0002622481,"domain_scores_codex":[0.9979892,0.000400892,0.0006347722,0.0001398931,0.0005377672,0.0002974745],"domain_scores_gemma":[0.9702163,0.02767868,0.001483999,0.0002246558,0.0003287381,0.00006766809],"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":[0.0004459946,0.0006606579,0.2969039,0.00005315332,0.001093021,0.000009815174,0.001144754,0.00006256021,0.001433381,0.4784022,0.006057876,0.2137326],"study_design_scores_gemma":[0.0008495059,0.001175073,0.3132578,0.00004294872,0.0009970736,0.00001027742,0.000351952,0.00122221,0.0003715074,0.6809965,0.0005496959,0.000175525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013303,0.000033578,0.8942748,0.003225907,0.00006164232,0.0004945815,0.0005130832,0.00002022333,0.00004591216],"genre_scores_gemma":[0.9643841,0.00004938514,0.03494005,0.0001721625,0.0002621995,0.00004145877,0.000003723052,0.00001851907,0.0001283855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8630539,"threshold_uncertainty_score":0.5370393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05773673034347347,"score_gpt":0.3931632132081859,"score_spread":0.3354264828647124,"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."}}