{"id":"W2954642664","doi":"10.1177/2515245919858072","title":"Failing Grade: 89% of Introduction-to-Psychology Textbooks That Define or Explain Statistical Significance Do So Incorrectly","year":2019,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Fallacy; Psychology; Odds; Significance testing; Experimental psychology; Statistical significance; Epistemology; Logistic regression; Cognition; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01265207,0.0002095318,0.000529913,0.0003398732,0.0001143713,0.0000809047,0.0005825856,0.0001242997,0.0004779022],"category_scores_gemma":[0.05061052,0.0001482273,0.00002438598,0.001211632,0.001173203,0.0005649418,0.000142926,0.0005245032,0.00001117253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000504297,"about_ca_system_score_gemma":0.00008052639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001944677,"about_ca_topic_score_gemma":0.00004272852,"domain_scores_codex":[0.9957578,0.0016842,0.0006661693,0.001057122,0.0003666507,0.0004680956],"domain_scores_gemma":[0.9781496,0.02042954,0.0006591556,0.0005286603,0.0001006571,0.0001324044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008593317,0.0005845344,0.0263029,0.0001429092,0.000006179644,0.00001537908,0.001824183,0.00007256865,0.01063378,0.2256199,0.0005271347,0.7334112],"study_design_scores_gemma":[0.0009505267,0.001051815,0.03086558,0.00008418246,0.0000185025,0.0001044416,0.004564708,0.0002932926,0.003123735,0.9007072,0.05775673,0.0004792371],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2210622,0.001186512,0.7639701,0.002738715,0.003851286,0.0009134213,0.00002109255,0.00005080373,0.006205916],"genre_scores_gemma":[0.1553046,0.001074723,0.8429264,0.0004292302,0.00007722198,0.0000624352,0.000001221002,0.000009148903,0.0001149947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7329319,"threshold_uncertainty_score":0.9573866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2283246623473483,"score_gpt":0.6279325644064597,"score_spread":0.3996079020591115,"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."}}