{"id":"W3014838344","doi":"","title":"Equivalence testing for standardized effect sizes in linear regression","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Frequentist inference; Equivalence (formal languages); Mathematics; Null hypothesis; Statistics; Statistical hypothesis testing; Type I and type II errors; Statistical power; Bayesian probability; Linear regression; Econometrics; Regression analysis; Computer science; Bayesian inference; Discrete mathematics","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":[0.0008221223,0.0003230444,0.0007196476,0.0001065029,0.00008790634,0.0000317946,0.0004603303,0.0002706152,0.00004400943],"category_scores_gemma":[0.01508472,0.0002970494,0.0001698041,0.0003460945,0.0001006818,0.0000546892,0.0006630038,0.0006062577,0.000008741813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509201,"about_ca_system_score_gemma":0.0001483545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003603638,"about_ca_topic_score_gemma":0.000008144324,"domain_scores_codex":[0.9981056,0.0003715074,0.0003036487,0.0007912618,0.0001000002,0.0003279629],"domain_scores_gemma":[0.9905459,0.008389826,0.0002858368,0.0004555914,0.000178345,0.0001444779],"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":[0.00408934,0.0004159903,0.02833498,0.01359726,0.0003268006,0.001372214,0.0008373144,0.01004453,0.005427429,0.9046338,0.001912349,0.02900805],"study_design_scores_gemma":[0.001363345,0.0003726477,0.0005396999,0.001530978,0.0001544266,0.000001021692,0.00004057762,0.20913,0.0009137589,0.7854806,0.00006834229,0.0004045811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2576039,0.00002721559,0.7395822,0.00004955687,0.0003032521,0.0008328899,0.000164521,0.0001452263,0.001291297],"genre_scores_gemma":[0.7522667,0.00002184795,0.2473803,0.00002358594,0.00008651261,0.000005229974,0.00000799713,0.00003220515,0.0001756505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4946629,"threshold_uncertainty_score":0.9999481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3127380090906889,"score_gpt":0.3317801632222279,"score_spread":0.01904215413153892,"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."}}