{"id":"W3204460067","doi":"10.1080/01621459.2021.1987250","title":"Model-assisted estimation through random forests in finite population sampling","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":31,"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; Point estimation; Computer science; Estimation; Population; Small area estimation; Variety (cybernetics); Sampling (signal processing); Calibration; Sample (material); Econometrics; Variable (mathematics); Random effects model; Sample size determination; Mathematics; 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":[0.0001681153,0.000120675,0.0001747806,0.00007629039,0.00008424198,0.00005015434,0.0003843974,0.00008026695,0.000003624974],"category_scores_gemma":[0.00007507119,0.0001327536,0.00006822342,0.0007430874,0.0000171081,0.0009331038,0.0001192086,0.0001345949,0.00001076409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005753921,"about_ca_system_score_gemma":0.00003216613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006868617,"about_ca_topic_score_gemma":0.000063412,"domain_scores_codex":[0.9990423,0.0001052162,0.000155827,0.0004473232,0.00005888156,0.0001904966],"domain_scores_gemma":[0.9994122,0.0001167493,0.00008788868,0.0002645019,0.00003609278,0.00008260883],"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":[0.00004024684,0.00001652517,0.001796578,0.00001063374,0.000004777392,0.00002025012,0.0004121925,0.776856,0.00004353893,0.2150471,0.00001180158,0.005740334],"study_design_scores_gemma":[0.0008816359,0.00001823085,0.003544361,0.0000157973,0.000008027842,8.500389e-7,0.000004477265,0.8181155,0.00002904289,0.177248,0.00001199407,0.0001221209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07345711,0.0000129196,0.9254414,0.0002733794,0.00005161328,0.000144285,0.000001496201,0.000113653,0.0005041684],"genre_scores_gemma":[0.7224869,0.000007497029,0.277214,0.0002326899,0.00001319224,3.536882e-7,0.000005614278,0.000005490071,0.00003436096],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6490297,"threshold_uncertainty_score":0.5413533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.166556126151278,"score_gpt":0.2390875085059244,"score_spread":0.0725313823546464,"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."}}