{"id":"W3008477519","doi":"10.1080/01621459.2021.1987250","title":"Model-Assisted Estimation Through Random Forests in Finite Population Sampling","year":2021,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Variance (accounting); Statistics; Random forest; Estimation; Point estimation; Computer science; Random effects model; Population; Sampling (signal processing); Simple random sample; Small area estimation; Calibration; Sampling design; Sample (material); Econometrics; Random variable; Confidence interval; Mathematics; Machine learning; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001773036,0.0002048272,0.0007554308,0.0001238789,0.00009041172,0.0003134173,0.000641114,0.0001466671,0.000002272692],"category_scores_gemma":[0.003574891,0.0001566992,0.000244966,0.0004752681,0.00003303431,0.0003906409,0.0003751029,0.000966318,6.037349e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009807729,"about_ca_system_score_gemma":0.0003249598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000256501,"about_ca_topic_score_gemma":0.0001417604,"domain_scores_codex":[0.9965978,0.001010859,0.001006652,0.0002894276,0.0008373059,0.000258012],"domain_scores_gemma":[0.9942785,0.001633929,0.003274192,0.0003683717,0.0003794364,0.00006557548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001223266,0.0002095624,0.01634568,0.00008037684,0.0001824637,0.00002326519,0.001536461,0.7238056,0.0001015581,0.01900444,0.0004506917,0.2381376],"study_design_scores_gemma":[0.0003731288,0.00002481078,0.1520806,0.0001597559,0.00005395887,0.000006668457,0.000007348732,0.6276478,0.00001028237,0.2195158,0.000003958945,0.0001158535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03172408,0.00006207192,0.9655226,0.001788273,0.0006349235,0.0001766769,0.00002566072,0.00001579565,0.00004992801],"genre_scores_gemma":[0.4686358,0.00002878989,0.5310311,0.0002031685,0.00006070912,0.000004255898,0.00001290242,0.000008505063,0.00001469242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4369117,"threshold_uncertainty_score":0.6390008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0405564620954532,"score_gpt":0.3468353973952853,"score_spread":0.3062789352998321,"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."}}