{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1754809,0.002019411,0.002239704,0.003385319,0.001696334,0.002385365,0.004201565,0.004933618,0.002816979],"category_scores_gemma":[0.6429169,0.0008604918,0.004689564,0.002988816,0.009642933,0.003501626,0.002998276,0.00526684,0.0004666478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001724426,"about_ca_system_score_gemma":0.001826238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003277531,"about_ca_topic_score_gemma":0.002489066,"domain_scores_codex":[0.7623481,0.2000997,0.009267829,0.012635,0.01456714,0.001082336],"domain_scores_gemma":[0.1354921,0.794229,0.02062924,0.0385542,0.01022685,0.0008686045],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01056798,0.001559081,0.254308,0.006463693,0.02471622,0.003789266,0.008243445,0.1105095,0.03212792,0.1114669,0.008155685,0.4280924],"study_design_scores_gemma":[0.001829555,0.009012339,0.1817741,0.002415235,0.007677364,0.004602784,0.002628845,0.2032953,0.05463266,0.498912,0.03224913,0.0009708045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2392166,0.006278767,0.7369993,0.002583622,0.0007174882,0.001014129,0.0007817763,0.0007932735,0.011615],"genre_scores_gemma":[0.8466094,0.001052207,0.1484787,0.0009871363,0.0003262179,0.0005785254,0.0007300428,0.0004380121,0.000799832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8245191,"threshold_uncertainty_score":0.9280427,"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."}}