{"id":"W2917498738","doi":"10.1080/01621459.2023.2183130","title":"Hypotheses Testing from Complex Survey Data Using Bootstrap Weights: A Unified Approach","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Stroke Foundation; National Science Foundation","keywords":"Type I and type II errors; Statistics; Categorical variable; Wald test; Statistical hypothesis testing; Computer science; Likelihood-ratio test; Goodness of fit; Mathematics; Nominal level; Econometrics; Data mining; Confidence interval","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00311677,0.0001626007,0.0006200397,0.00008525021,0.0001832234,0.0001172994,0.0007359084,0.00004898657,0.00004059674],"category_scores_gemma":[0.06274059,0.0001076555,0.00006440989,0.0009844878,0.000173638,0.0001313655,0.0002331059,0.0003855235,0.000008396526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002412085,"about_ca_system_score_gemma":0.0001717176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009156512,"about_ca_topic_score_gemma":0.00002894124,"domain_scores_codex":[0.9962088,0.001617441,0.0007904056,0.000227264,0.0008282553,0.0003278199],"domain_scores_gemma":[0.9651784,0.03192464,0.001954598,0.0004227094,0.0004027183,0.0001169809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005063513,0.001010472,0.6640185,0.000165168,0.001675878,0.00009381431,0.0008256162,0.00008621065,0.007973016,0.1056003,0.07227246,0.1457721],"study_design_scores_gemma":[0.0002108744,0.00006504366,0.5832049,0.00004704552,0.0001671429,0.000007649231,0.0001736045,0.06287391,0.00001725576,0.3530466,0.00005555004,0.0001304174],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1069491,0.000005221381,0.889568,0.0001933992,0.000185963,0.0001167841,0.002644779,0.00003484394,0.0003019139],"genre_scores_gemma":[0.232178,0.000005683988,0.767425,0.00009735593,0.0001988151,9.335467e-7,0.00005009724,0.00002307718,0.00002107321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2474462,"threshold_uncertainty_score":0.9451544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5140034967384134,"score_gpt":0.454645358952512,"score_spread":0.05935813778590143,"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."}}