{"id":"W3204009844","doi":"10.21203/rs.3.rs-7246683/v1","title":"Sample Size Determination for Skewed and Heavy-tailed Distributions","year":2025,"lang":"en","type":"article","venue":"Research Square","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"MacEwan University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Kurtosis; Skewness; Heavy-tailed distribution; Sample size determination; Mathematics; Sample (material); Monte Carlo method; Distribution (mathematics); Statistics; Applied mathematics; Statistical physics; Pareto principle; Central limit theorem; Domain (mathematical analysis); Degrees of freedom (physics and chemistry); Limit (mathematics); Probability distribution; Mathematical analysis","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001461532,0.00007285985,0.0001149969,0.0001312426,0.0004285829,0.0002187775,0.000335937,0.00006791732,0.000007075055],"category_scores_gemma":[0.002908515,0.00006486807,0.00004719146,0.0005735946,0.00006990499,0.0001909747,0.0002296875,0.0001546847,0.000002073049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006925217,"about_ca_system_score_gemma":0.0001526667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003252168,"about_ca_topic_score_gemma":0.00001935821,"domain_scores_codex":[0.9987105,0.0002612387,0.0001297214,0.0003236391,0.000223899,0.0003509862],"domain_scores_gemma":[0.9956767,0.003487611,0.00001834478,0.0003656687,0.0003598376,0.00009185642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000022037,0.00004593013,0.0003033939,0.0001181503,0.00000654693,0.000001532846,0.0001366154,3.902508e-7,0.0005049083,0.6600788,0.00203056,0.3367511],"study_design_scores_gemma":[0.0006830957,0.0001913867,0.007227207,0.000111762,0.000005287838,0.000002236914,0.00002846395,0.08692415,0.005575242,0.8787453,0.02036647,0.0001394696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001432539,0.000180235,0.9929149,0.0040759,0.00007841764,0.0005534317,0.00005772385,0.00005567073,0.0006511721],"genre_scores_gemma":[0.4047469,0.00003630834,0.5941728,0.0000676698,0.00003788023,0.0002062837,0.000009594177,0.000004509433,0.0007181109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4033143,"threshold_uncertainty_score":0.3481974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04488157809082638,"score_gpt":0.4200325795139338,"score_spread":0.3751510014231074,"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."}}