{"id":"W2770123802","doi":"10.1002/cjs.11527","title":"Estimating prediction error for complex samples","year":2019,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health","keywords":"Estimator; Statistics; Sampling (signal processing); Generalization; Context (archaeology); Sample size determination; Computer science; Population; Sample (material); Mean squared error; Econometrics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008916919,0.00028806,0.0007907943,0.0002818088,0.0001566669,0.0001830984,0.0004208577,0.0002508272,0.0003470648],"category_scores_gemma":[0.01005179,0.0002743047,0.0001453972,0.00006767064,0.0001475382,0.00004968678,0.00004520504,0.0006929978,0.000005229356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003024043,"about_ca_system_score_gemma":0.002842447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008270476,"about_ca_topic_score_gemma":0.002466827,"domain_scores_codex":[0.997812,0.0001293974,0.001113953,0.0002356195,0.0002817631,0.0004272246],"domain_scores_gemma":[0.9936493,0.003271943,0.001139209,0.0003189828,0.001024688,0.0005958775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000372916,0.00003376751,0.001586296,0.002875632,0.000282346,0.0001000374,0.000766281,0.0009833496,0.0000247447,0.7570809,0.1847238,0.05150556],"study_design_scores_gemma":[0.0003415239,0.0002016199,0.00210086,0.000703179,0.0002966267,0.00006272517,0.00008470245,0.08360048,0.000006225835,0.9095051,0.002851767,0.0002451724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002966889,0.00006464984,0.9712914,0.0001714401,0.002948863,0.0004812924,0.02443245,0.00001112983,0.000302087],"genre_scores_gemma":[0.01339031,0.000005104485,0.9855219,0.00008464771,0.0006972721,0.00001185211,0.0001655395,0.00005916122,0.00006417711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.181872,"threshold_uncertainty_score":0.9999709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2079316552992227,"score_gpt":0.3905411675951317,"score_spread":0.182609512295909,"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."}}