{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07807393,0.001795744,0.003713791,0.007807736,0.001369268,0.003557839,0.004104731,0.00234298,0.004140011],"category_scores_gemma":[0.1685132,0.001552033,0.002585411,0.005483031,0.003722135,0.005558698,0.0060769,0.004467129,0.001206803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001309508,"about_ca_system_score_gemma":0.003210273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001166576,"about_ca_topic_score_gemma":0.001136589,"domain_scores_codex":[0.9371778,0.05045543,0.002500758,0.0026195,0.006791479,0.0004550485],"domain_scores_gemma":[0.8929196,0.08568233,0.004270361,0.009983753,0.006358099,0.0007858313],"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":[0.0001618477,0.000306161,0.005499927,0.001158035,0.0007168702,0.0004877547,0.001453807,0.04477862,0.001934794,0.5387155,0.006067054,0.3987196],"study_design_scores_gemma":[0.0001299385,0.0002569072,0.002265163,0.0004230224,0.0001464179,0.0002243973,0.0003017309,0.304254,0.001256626,0.6800448,0.01058551,0.0001114336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008452565,0.0001024628,0.9984826,0.00008021119,0.00002223982,0.0001477092,0.00003265321,0.00007052051,0.0002164108],"genre_scores_gemma":[0.03070091,0.0004554278,0.9661479,0.0001443371,0.0001621858,0.001847389,0.0001762113,0.0000765428,0.0002890916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07807393,"threshold_uncertainty_score":0.4128993,"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."}}