{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008442155,0.00009982349,0.000500347,0.0000549586,0.00002408743,0.00002067145,0.0001129041,0.00002749545,0.000517941],"category_scores_gemma":[0.0002419393,0.00009210029,0.0000308103,0.00004618023,0.00007269175,0.00008813822,0.0000295258,0.00007774578,0.00002636313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003346696,"about_ca_system_score_gemma":0.000009173405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001643411,"about_ca_topic_score_gemma":0.000123754,"domain_scores_codex":[0.9989378,0.00003664482,0.0006490409,0.0002134893,0.00003509281,0.0001278832],"domain_scores_gemma":[0.9992968,0.0002172769,0.000307362,0.0001073137,0.00002152288,0.00004974069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003570029,0.00008411556,0.573021,0.0002977079,0.00008112375,5.41246e-7,0.0000269157,0.001456661,0.00000223711,0.4133779,0.002887629,0.008728495],"study_design_scores_gemma":[0.0003481116,0.00007999872,0.368591,0.0003413666,0.0000224269,0.000007768412,0.000001640766,0.558099,0.000007002444,0.06261401,0.009664219,0.0002234501],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01509898,0.01586641,0.9528916,0.000370179,0.00008685254,0.0001797452,0.001144545,0.000008367627,0.01435326],"genre_scores_gemma":[0.8344861,0.001364408,0.1635833,0.0002420485,0.00003124199,0.000009070067,0.000130377,0.000009478209,0.0001440042],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8193871,"threshold_uncertainty_score":0.567109,"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."}}