{"id":"W2011971374","doi":"10.1111/j.1751-5823.2006.tb00297.x","title":"Comparison of Benchmarking Methods with and without a Survey Error Model","year":2006,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Benchmarking; Statistics; Mean squared error; Autoregressive model; Computer science; Multiplicative function; Regression analysis; Regression; Econometrics; Mathematics; Data mining","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":[0.04490513,0.00100981,0.001928651,0.003997948,0.0005278896,0.001533851,0.002613455,0.001717967,0.002907841],"category_scores_gemma":[0.1591102,0.0005034414,0.001427981,0.004204381,0.0008607797,0.002936473,0.002654919,0.0008678094,0.0006632057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001419559,"about_ca_system_score_gemma":0.002203592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004150692,"about_ca_topic_score_gemma":0.002208352,"domain_scores_codex":[0.9372869,0.05301036,0.001733249,0.001801793,0.005399335,0.0007684347],"domain_scores_gemma":[0.8564326,0.1112278,0.006089939,0.01336945,0.01208522,0.0007950041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001187228,0.0003725146,0.02725183,0.001288203,0.001066819,0.0001794896,0.0005587389,0.2383049,0.001217482,0.07729568,0.005313907,0.6459632],"study_design_scores_gemma":[0.0001380763,0.0004367438,0.01368799,0.0002954769,0.0001780183,0.0002246127,0.00027109,0.9495958,0.002053917,0.0283117,0.004717198,0.0000893919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07564695,0.002041753,0.9134896,0.0007088856,0.0002668278,0.0002932699,0.0003645554,0.001054197,0.006133879],"genre_scores_gemma":[0.6141451,0.001159789,0.3797388,0.0002327585,0.0001732245,0.0005600838,0.0009700921,0.0003112426,0.002708904],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04490513,"threshold_uncertainty_score":0.2374839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2413521849383838,"score_gpt":0.427689485747408,"score_spread":0.1863373008090242,"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."}}