{"id":"W4411439860","doi":"10.1007/978-3-662-69359-9_189","title":"E-values (E for Expectation) in Hypothesis Testing","year":2025,"lang":"en","type":"book-chapter","venue":"International Encyclopedia of Statistical Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Psychology; Econometrics; Statistics; Mathematics; Computer science","routes":{"ca_aff":true,"ca_fund":false,"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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002659057,0.0003011207,0.0007920893,0.0004867426,0.00007772737,0.00004675044,0.001037474,0.0002125846,0.0006504674],"category_scores_gemma":[0.4164,0.0002823699,0.0001205153,0.000202171,0.001263607,0.0001220118,0.0002390397,0.0003202292,0.00001636012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002693669,"about_ca_system_score_gemma":0.0006319451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003609643,"about_ca_topic_score_gemma":0.00002137335,"domain_scores_codex":[0.9959664,0.00006142365,0.001642605,0.0007697067,0.001214601,0.000345275],"domain_scores_gemma":[0.8477604,0.1504029,0.0005465946,0.0002924732,0.0008750053,0.0001226885],"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":[0.00005805131,0.00006307573,0.00008135577,0.0001338975,0.00002779296,0.000009187633,0.00003823727,0.000003070806,0.00001910035,0.9053612,0.002109457,0.0920956],"study_design_scores_gemma":[0.0004182074,0.0001007178,0.0007409871,0.0005889289,0.00006685939,0.000001697642,0.0000128587,0.001179451,0.00004683893,0.9933561,0.003226458,0.0002608905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.00003665251,0.0000132909,0.222611,0.0002094293,0.001137854,0.000639572,0.001484212,0.0000360911,0.773832],"genre_scores_gemma":[0.0004732165,0.00007076089,0.9330183,0.00006672271,0.000267782,0.00008149774,0.000006142126,0.00003032594,0.0659853],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7104073,"threshold_uncertainty_score":0.9999629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3553849541450152,"score_gpt":0.5088764397267439,"score_spread":0.1534914855817287,"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."}}