{"id":"W2121156811","doi":"10.1006/anbe.2000.1576","title":"Assessing the robustness of randomization tests: examples from behavioural studies","year":2001,"lang":"en","type":"article","venue":"Animal Behaviour","topic":"Animal Behavior and Welfare Studies","field":"Veterinary","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Nonparametric statistics; Type I and type II errors; Robustness (evolution); Monte Carlo method; Parametric statistics; Statistical power; Computer science; Statistical hypothesis testing; Statistics; Econometrics; 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":[],"consensus_categories":[],"category_scores_codex":[0.000385421,0.0003428891,0.0006026398,0.000082693,0.0005067938,0.000104142,0.0003513376,0.000118447,0.0002553495],"category_scores_gemma":[0.0001832311,0.0002368726,0.0002291602,0.0002986282,0.0003461397,0.0005574228,0.000255828,0.0002479215,0.00001784277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007284004,"about_ca_system_score_gemma":0.0000313158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001517744,"about_ca_topic_score_gemma":0.0001420508,"domain_scores_codex":[0.9979057,0.0002247877,0.0006471123,0.0004247884,0.0004086113,0.0003889588],"domain_scores_gemma":[0.9984522,0.0004209328,0.0003163717,0.0003847533,0.0003642562,0.00006149806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006817746,0.0002043533,0.9783133,0.000009859379,0.00009966918,0.0001228565,0.001059289,0.000009745789,0.01784045,0.0001321002,0.0004091164,0.001117534],"study_design_scores_gemma":[0.001569236,0.0004255797,0.9861763,0.00008010679,0.0005432624,0.0000805005,0.01021172,0.00004242095,0.0004751918,0.00003167399,0.00007332662,0.0002906864],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962745,0.001943041,0.0001913438,0.0003815384,0.0003168635,0.0003809261,0.00006360212,0.0001385195,0.0003096547],"genre_scores_gemma":[0.9987172,0.0002223118,0.0005316397,0.00003761554,0.0002184943,0.00008574945,0.00005268909,0.0000485758,0.00008572249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01736525,"threshold_uncertainty_score":0.9659383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.206900499484041,"score_gpt":0.4115062756873492,"score_spread":0.2046057762033081,"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."}}