{"id":"W4396860058","doi":"10.1080/01621459.2024.2353948","title":"Generalized Data Thinning Using Sufficient Statistics","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; W. M. Keck Foundation; National Institutes of Health; National Science Foundation","keywords":"Generalization; Random variable; Mathematics; Thinning; Inference; Sum of normally distributed random variables; Set (abstract data type); Variables; Sample (material); Exponential function; Statistics; Variable (mathematics); Function (biology); Exponential family; Applied mathematics; Computer science; Marginal distribution; Artificial intelligence; Mathematical analysis","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":[0.002577315,0.0001459167,0.0004623547,0.0000788934,0.0001253478,0.0001938891,0.000538772,0.00003952401,0.0001135632],"category_scores_gemma":[0.02001697,0.00009232076,0.00007449397,0.0004413699,0.0001387543,0.0001239498,0.000203434,0.0004891546,0.000008188504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004870221,"about_ca_system_score_gemma":0.0002816645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000734427,"about_ca_topic_score_gemma":0.000005501627,"domain_scores_codex":[0.9971169,0.0006646211,0.0008083351,0.0001966008,0.0009289492,0.000284594],"domain_scores_gemma":[0.9902766,0.007867134,0.001066454,0.0003490169,0.0003316091,0.0001091751],"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":[0.00006879647,0.000163252,0.002895618,0.0001190835,0.0004183818,0.00008239989,0.0004511188,0.0001264208,0.001401654,0.8486188,0.09989749,0.045757],"study_design_scores_gemma":[0.0003262037,0.0002519649,0.01061469,0.0002661361,0.0008459438,0.00008751143,0.0002453232,0.3574569,0.000109298,0.6252235,0.004282659,0.0002898491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06012838,0.00008465625,0.9367835,0.0006817143,0.000948253,0.00008521189,0.001160656,0.00002319821,0.0001044504],"genre_scores_gemma":[0.1231395,0.00002918128,0.8760545,0.0002378792,0.0003558217,7.626206e-7,0.000008330636,0.0000281854,0.0001458458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3573305,"threshold_uncertainty_score":0.9882379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1489105408152893,"score_gpt":0.44730948182901,"score_spread":0.2983989410137208,"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."}}