{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03573442,0.00103222,0.002007582,0.001932712,0.0006208281,0.00225146,0.002367866,0.00207948,0.001626753],"category_scores_gemma":[0.1603749,0.0008651707,0.001073683,0.001772843,0.002675414,0.003943492,0.002894508,0.002992264,0.0003458991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001831118,"about_ca_system_score_gemma":0.001538888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00570125,"about_ca_topic_score_gemma":0.003349847,"domain_scores_codex":[0.9881158,0.007156698,0.0006909038,0.002078701,0.001645452,0.0003124673],"domain_scores_gemma":[0.8772948,0.1047424,0.005667777,0.007955162,0.003908379,0.0004314347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001836946,0.0001041457,0.01822502,0.0002423355,0.0004332602,0.000192853,0.0003945892,0.6627637,0.0009972034,0.1990245,0.002171944,0.1152669],"study_design_scores_gemma":[0.00001969117,0.00003534952,0.00185969,0.00003582171,0.00001889062,0.00004130835,0.00002388125,0.8941618,0.0004245032,0.1026814,0.0006803938,0.00001734109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01719564,0.0002930666,0.9815663,0.0002466431,0.00003570239,0.00004693147,0.00007246773,0.0001053464,0.0004379309],"genre_scores_gemma":[0.5083103,0.0008565677,0.4864498,0.0004288976,0.0001695387,0.0005175417,0.0007769602,0.0001560147,0.002334315],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03573442,"threshold_uncertainty_score":0.188984,"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."}}