{"id":"W7064367153","doi":"","title":"Beyond the traditional simulation design for evaluating type 1 error: from ‘theoretical’ to ‘empirical’ null","year":2018,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Particle Detector Development and Performance","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; Toronto Public Health","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto","keywords":"Association (psychology); Null hypothesis; Sample (material); Type I and type II errors; Scale (ratio); Sample size determination; Statistical hypothesis testing; Statistical power","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020288,0.0001383527,0.0001811904,0.00001863416,0.0002692824,0.00001628603,0.0002262882,0.00007721491,0.02242143],"category_scores_gemma":[0.00001735137,0.0001379282,0.00009188617,0.00005576254,0.00005352759,0.0001530925,0.00001805129,0.00007335003,0.00006361787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008128812,"about_ca_system_score_gemma":0.0001319914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001545581,"about_ca_topic_score_gemma":0.0008365691,"domain_scores_codex":[0.9992556,0.00005119915,0.0001004846,0.0002166958,0.0002148622,0.0001611853],"domain_scores_gemma":[0.9991069,0.000291936,0.0001484646,0.0001654983,0.0002230832,0.00006414001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01978844,0.0008439165,0.00797433,0.0002685008,0.002677359,0.000002485289,0.336664,0.02301363,0.01901625,0.03935038,0.04668443,0.5037163],"study_design_scores_gemma":[0.003023925,0.00196852,0.3940734,0.0002755904,0.0009955707,1.257066e-7,0.0360239,0.5230248,0.005879014,0.02694515,0.006354216,0.00143584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9612118,0.00004028571,0.02038827,0.0001957276,0.00040319,0.0005499178,0.0001122267,0.00001858712,0.01708001],"genre_scores_gemma":[0.9863054,0.000001513974,0.01104686,0.00002203739,0.0002240836,0.000002627231,0.0006744491,0.0000138359,0.001709158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5022805,"threshold_uncertainty_score":0.9784722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0757174396159749,"score_gpt":0.3355966480946286,"score_spread":0.2598792084786538,"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."}}