{"id":"W4246572769","doi":"10.7287/peerj.preprints.3411","title":"Manipulating the alpha level cannot cure significance testing","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of New Brunswick; Queen's University","funders":"","keywords":"Significance testing; Statistical significance; Statistical hypothesis testing; Inference; Econometrics; Statistical inference; Sample size determination; MAGIC (telescope); Multiple comparisons problem; Value (mathematics); Variable (mathematics); Statistics; Computer science; Psychology; Mathematics; Artificial intelligence; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.003659938,0.0002933659,0.0003319256,0.0001166029,0.0006487974,0.0007504804,0.002893744,0.0002332474,0.0004668305],"category_scores_gemma":[0.004262607,0.0001659135,0.0001571142,0.0007924807,0.0002767517,0.00007516091,0.002130195,0.0007077451,0.0003094878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006473597,"about_ca_system_score_gemma":0.0002451934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002020098,"about_ca_topic_score_gemma":0.000384103,"domain_scores_codex":[0.9964237,0.0001292289,0.0009279018,0.0009989283,0.001157012,0.0003632566],"domain_scores_gemma":[0.9937912,0.002286712,0.0007969366,0.002068208,0.0009671174,0.00008987274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008213735,0.00008521721,0.01388692,0.00004000613,0.00004149558,0.000007003813,0.0006440976,0.004807607,0.0009642529,0.03294258,0.7043616,0.242211],"study_design_scores_gemma":[0.00009273986,0.00006744932,0.01797853,0.0002764685,0.00003915322,0.00003007916,0.0004157068,0.3049329,0.001625696,0.5618622,0.1118589,0.000820226],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06762759,0.0001439132,0.6507779,0.01334996,0.001407441,0.00252578,0.0003026643,0.001383198,0.2624815],"genre_scores_gemma":[0.7959235,0.000002758416,0.1940734,0.0004565325,0.0007023903,0.0002268769,0.00001065196,0.0000313987,0.008572547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7282959,"threshold_uncertainty_score":0.72369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6247379511487856,"score_gpt":0.4651673220119816,"score_spread":0.159570629136804,"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."}}