{"id":"W2097184733","doi":"10.3758/brm.41.3.664","title":"Randomization tests and the unequal-N/unequal-variance problem","year":2009,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Variance (accounting); Statistics; Value (mathematics); Analysis of variance; Type I and type II errors; Word error rate; Mathematics; Computer science; Econometrics; Algorithm; Speech recognition; Economics","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":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.130204,0.0002684059,0.000701457,0.000547941,0.0007807363,0.001081218,0.001434044,0.000181609,0.0003485864],"category_scores_gemma":[0.0295601,0.0001547276,0.0001788397,0.002809491,0.001104982,0.0006152187,0.0004034093,0.0006181231,0.0001083054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025186,"about_ca_system_score_gemma":0.0001754634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009767659,"about_ca_topic_score_gemma":0.000004609774,"domain_scores_codex":[0.9625892,0.03114322,0.001125793,0.001034236,0.003282905,0.0008246419],"domain_scores_gemma":[0.9751085,0.02199485,0.0002608069,0.001317597,0.0009873183,0.0003309188],"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":[0.001426726,0.0002091845,0.0004520642,0.000003453317,0.00000771756,0.00002273943,0.001558764,0.00009330975,0.1112695,0.03581606,0.0008696936,0.8482708],"study_design_scores_gemma":[0.04220274,0.002429456,0.05318082,0.0001642974,0.0001461014,0.0001249596,0.005244955,0.04489345,0.1651471,0.6534899,0.03132764,0.001648677],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04472293,0.003083015,0.9244085,0.004957608,0.0003994636,0.005131354,0.00001175703,0.0001529144,0.01713246],"genre_scores_gemma":[0.1453581,0.0001038674,0.8496844,0.0002078078,0.0001056389,0.0004697984,0.000002384209,0.00002678597,0.004041207],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8466221,"threshold_uncertainty_score":0.9999558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5240400499227096,"score_gpt":0.6774203494091746,"score_spread":0.153380299486465,"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."}}