{"id":"W3032026822","doi":"10.1002/cjs.11551","title":"Correlated and misclassified binary observations in complex surveys","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Generalized estimating equation; Binary data; Binary number; Gee; Computer science; Sampling (signal processing); Data mining; Focus (optics); Statistics; Survey data collection; Econometrics; Mathematics; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005255318,0.0001020503,0.0002939722,0.0001136772,0.00006761253,0.00004996613,0.0001263414,0.00005971844,0.0002872017],"category_scores_gemma":[0.005036914,0.00009643054,0.00001915226,0.0002531167,0.0001320549,0.00005823991,0.000009865644,0.0002921428,0.0000033277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005433945,"about_ca_system_score_gemma":0.0005476883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007440863,"about_ca_topic_score_gemma":0.005865675,"domain_scores_codex":[0.9987881,0.0002857345,0.0005056379,0.00009483067,0.0001201422,0.0002056194],"domain_scores_gemma":[0.9974796,0.001390777,0.0001921769,0.00006834072,0.0002147628,0.0006543503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002041754,0.00003023081,0.06332549,0.000151615,0.00004725503,0.001321721,0.001705138,0.00001200563,0.0003692654,0.8616043,0.04904444,0.02236813],"study_design_scores_gemma":[0.0007109027,0.0002557172,0.5271018,0.0000876499,0.00004875716,0.00005754415,0.0003024195,0.01253963,0.000008615785,0.4570076,0.001685893,0.0001935033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01699862,0.00005423175,0.9797592,0.001671539,0.0001102069,0.00008560745,0.001000735,0.000004700232,0.0003152296],"genre_scores_gemma":[0.2816899,0.00001277912,0.7178949,0.0003177147,0.00003783331,6.364656e-7,0.00001508433,0.00001329342,0.00001776195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4637763,"threshold_uncertainty_score":0.603002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2547201797386306,"score_gpt":0.3368134296065589,"score_spread":0.08209324986792821,"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."}}