{"id":"W2982189774","doi":"10.3389/fevo.2019.00372","title":"Errors in Statistical Inference Under Model Misspecification: Evidence, Hypothesis Testing, and AIC","year":2019,"lang":"en","type":"article","venue":"Frontiers in Ecology and Evolution","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Institute of General Medical Sciences; Japan Society for the Promotion of Science","keywords":"Statistics; Frequentist inference; Type I and type II errors; Statistical hypothesis testing; Econometrics; Sample size determination; Statistical inference; Mathematics; Inference; Contrast (vision); Sample (material); Computer science; Bayesian inference; Bayesian probability; Artificial intelligence","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":[0.0005235677,0.0001155384,0.0002752761,0.0001588321,0.00004727002,0.00001364914,0.00007425503,0.0001635715,0.00004729169],"category_scores_gemma":[0.005121836,0.0001115182,0.000009169039,0.0001836055,0.0002030145,0.0001276083,0.00003760012,0.0002049482,0.00000706793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201728,"about_ca_system_score_gemma":0.00007533124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003320604,"about_ca_topic_score_gemma":0.000103187,"domain_scores_codex":[0.9988872,0.0001922193,0.0002923573,0.0003079375,0.00008352562,0.0002368018],"domain_scores_gemma":[0.9961699,0.003518365,0.00007541516,0.0001373612,0.00003960888,0.00005936821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004285187,0.00004914074,0.7796152,0.00007281551,0.000004877357,0.000002543591,0.0001058464,0.00008072767,0.00004349837,0.2106559,0.0005003167,0.00882631],"study_design_scores_gemma":[0.0001440207,0.00004288708,0.4450152,0.00003688358,0.000007052208,0.000002446494,0.00007527901,0.09303142,0.000001740579,0.4615769,0.000001588415,0.00006457551],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3315161,0.0001485213,0.6671493,0.000175345,0.0001358644,0.0002079018,0.000008036744,0.00001531522,0.0006436397],"genre_scores_gemma":[0.5232953,0.00004923288,0.4765543,0.00002996414,0.000006418701,0.00001478702,4.211977e-7,0.000004377662,0.00004519792],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3346,"threshold_uncertainty_score":0.6131686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09091726407699352,"score_gpt":0.3386140376743463,"score_spread":0.2476967735973528,"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."}}