{"id":"W4306802871","doi":"10.48550/arxiv.2210.08892","title":"Modified Wilcoxon-Mann-Whitney tests of stochastic dominance","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Statistics; Wilcoxon signed-rank test; Mathematics; Null hypothesis; Mann–Whitney U test; Univariate; Stochastic dominance; Dominance (genetics); Resampling; Econometrics; Population; Inference; Statistical hypothesis testing; Applied mathematics; Computer science; Artificial intelligence; Multivariate statistics; Biology; Demography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004488601,0.0003705271,0.0007634666,0.0002091091,0.000129848,0.00002062278,0.0009186231,0.0002448999,0.0006316314],"category_scores_gemma":[0.001489309,0.0004184673,0.0002383046,0.0004363212,0.0002139801,0.00006735636,0.001248456,0.0008090584,0.00001490621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001788243,"about_ca_system_score_gemma":0.0002230424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000878428,"about_ca_topic_score_gemma":0.00001757088,"domain_scores_codex":[0.9979165,0.0002997682,0.0004150454,0.0008365167,0.0001652675,0.0003668853],"domain_scores_gemma":[0.995921,0.002159862,0.0005766072,0.001007325,0.0001813531,0.0001539068],"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":[0.0001610241,0.000233468,0.0001687357,0.0004703212,0.00009762107,0.0001597631,0.0001614103,0.0170011,0.0000492304,0.980571,0.0002992494,0.0006270686],"study_design_scores_gemma":[0.0004559503,0.00009833018,0.0007093997,0.0002230469,0.0002379917,0.000003216726,0.00009922941,0.07363192,0.0000361911,0.9240682,0.00002170978,0.0004148501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1337843,0.0000377175,0.8607709,0.0000200476,0.0003674385,0.0004449741,0.0002871743,0.0000915867,0.00419589],"genre_scores_gemma":[0.9444893,0.00002417332,0.05438226,0.00002025158,0.00004699572,0.000005359939,0.00001502028,0.00003993549,0.0009767095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.810705,"threshold_uncertainty_score":0.9998267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1568879221479705,"score_gpt":0.2794844585672586,"score_spread":0.1225965364192881,"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."}}