{"id":"W2082880140","doi":"10.1198/016214506000000320","title":"Optimizing the Expected Overlap of Survey Samples via the Northwest Corner Rule","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Selection (genetic algorithm); Sampling (signal processing); Variance (accounting); Computer science; Mathematical optimization; Hypergeometric distribution; Statistics; Simple random sample; Mathematics; Focus (optics); Algorithm; Population; 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":[0.001836128,0.00007150464,0.0002023015,0.00003114268,0.0004670751,0.00006317292,0.0002799527,0.00003201601,0.00002843655],"category_scores_gemma":[0.001665869,0.00003717145,0.00008799776,0.0005104077,0.000311725,0.00009976251,0.000009321026,0.0001951199,0.000001609923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000178023,"about_ca_system_score_gemma":0.0001559188,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.024276,"about_ca_topic_score_gemma":0.01089998,"domain_scores_codex":[0.9975562,0.0009878969,0.0004638348,0.00006912355,0.0007529826,0.0001699708],"domain_scores_gemma":[0.9945598,0.003052864,0.001731444,0.00009690566,0.0005255184,0.00003348833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007016947,0.00007370656,0.9722793,0.000001987916,0.00006864543,9.701737e-7,0.00316862,0.01433458,0.00009419972,0.003243502,0.005146573,0.00151778],"study_design_scores_gemma":[0.0001398138,0.00003309615,0.995868,0.000009470335,0.00006439568,7.103743e-7,0.00152267,0.000373282,0.00002088368,0.0009935509,0.0009226876,0.00005148585],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8602563,0.00007556767,0.1328951,0.00490458,0.0005428364,0.000204532,0.0003576877,0.00002067965,0.0007427477],"genre_scores_gemma":[0.9959405,0.00002872658,0.003489357,0.0001537428,0.0001721285,0.000001577644,0.0000277422,0.00000707929,0.0001791351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1356842,"threshold_uncertainty_score":0.9822214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735220586405064,"score_gpt":0.2773536971453971,"score_spread":0.2600014912813465,"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."}}