{"id":"W2136733697","doi":"","title":"Estimating agreement coefficients from sample survey data","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Jackknife resampling; Statistics; Concordance; Mathematics; Cohen's kappa; Standard error; Correlation coefficient; Variance (accounting); Sampling (signal processing); Sample (material); Concordance correlation coefficient; Linearization; Computer science; Medicine; Nonlinear system; Accounting","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.2762679,0.0002991375,0.0007991191,0.0001885164,0.0003019797,0.000169002,0.003276782,0.0001864755,0.003435806],"category_scores_gemma":[0.313595,0.0002243194,0.00009042594,0.000956719,0.0002294131,0.0005006731,0.001646553,0.0003146736,0.001199535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008274973,"about_ca_system_score_gemma":0.0001082893,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02778998,"about_ca_topic_score_gemma":0.008170281,"domain_scores_codex":[0.938705,0.05395361,0.001854113,0.001529703,0.002826548,0.00113108],"domain_scores_gemma":[0.8328434,0.1601443,0.0007821087,0.004868311,0.0009122931,0.0004496143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001066463,0.0002511707,0.9368598,0.00000294907,0.00005658237,5.663479e-7,0.0004150082,0.0006549975,0.000272407,0.00003978461,0.01116959,0.05017048],"study_design_scores_gemma":[0.0003664162,0.00005511587,0.9806669,0.000008128782,0.00002015894,9.480149e-7,0.0001664747,0.006334972,0.0001991232,0.004805822,0.007109928,0.0002660559],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3556263,0.0002874872,0.6363247,0.0001099742,0.004616592,0.0002694585,0.002457933,0.00003000024,0.000277561],"genre_scores_gemma":[0.6076887,0.00000569372,0.3894898,0.0003987242,0.0003331569,0.00001112812,0.001900157,0.00001701324,0.0001556291],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2520625,"threshold_uncertainty_score":0.9995781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8726461020763974,"score_gpt":0.5551506380714631,"score_spread":0.3174954640049342,"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."}}