{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02965998,0.001027301,0.003279158,0.001615276,0.0009462652,0.001638211,0.003165356,0.001850331,0.003026946],"category_scores_gemma":[0.08436073,0.001288562,0.001464305,0.002089154,0.002512606,0.003123993,0.003690838,0.002435399,0.0007594096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201309,"about_ca_system_score_gemma":0.002423492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002376948,"about_ca_topic_score_gemma":0.001908241,"domain_scores_codex":[0.9657081,0.02526357,0.001168918,0.0041467,0.002909789,0.0008028551],"domain_scores_gemma":[0.9457967,0.04287566,0.003099558,0.004788468,0.002748341,0.0006912397],"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":[0.001027068,0.0004135554,0.01180578,0.0003177969,0.0004068165,0.0002740479,0.0006389375,0.5725906,0.003027636,0.1722098,0.003625054,0.2336629],"study_design_scores_gemma":[0.000301858,0.0004081056,0.001689397,0.00008309199,0.00006792774,0.0001475356,0.0001198713,0.9009958,0.003663204,0.08890354,0.003575581,0.00004409537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01560382,0.00009775416,0.9827605,0.0001459745,0.00001705654,0.0001798341,0.00006019503,0.0001144088,0.001020355],"genre_scores_gemma":[0.1697203,0.0001553093,0.82644,0.0002360801,0.00005392691,0.001393711,0.0003289729,0.000116925,0.001554905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02965998,"threshold_uncertainty_score":0.1568588,"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."}}