{"id":"W2344569906","doi":"10.1186/s13104-016-2045-z","title":"Accuracy when inferential statistics are used as measurement tools","year":2016,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Type I and type II errors; Statistics; Null hypothesis; Observational error; Statistical power; Mathematics; Standard deviation; Monte Carlo method; Statistical hypothesis testing; Nominal level; p-value; Type (biology); Statistical inference; Sample size determination; Confidence interval","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":["metaresearch"],"category_scores_codex":[0.4217889,0.002396206,0.005058275,0.01191402,0.002209002,0.01557812,0.005389021,0.00665669,0.005799716],"category_scores_gemma":[0.8810715,0.002115743,0.003681871,0.01554427,0.01696806,0.01725849,0.01015433,0.009920707,0.002397471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005444127,"about_ca_system_score_gemma":0.008091112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001774725,"about_ca_topic_score_gemma":0.001069891,"domain_scores_codex":[0.2854448,0.5491458,0.05045721,0.02176788,0.09108925,0.00209513],"domain_scores_gemma":[0.04420524,0.8720114,0.02649045,0.04039377,0.01636571,0.0005334622],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001225979,0.0002394087,0.02988591,0.01703497,0.004776897,0.0006754694,0.01189598,0.01387671,0.001226702,0.4877706,0.02630888,0.4050825],"study_design_scores_gemma":[0.0002123137,0.0004345599,0.009921839,0.0109685,0.001300531,0.0009877415,0.001667984,0.03270552,0.003294722,0.8624796,0.07571029,0.0003163918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01075888,0.02009892,0.9183067,0.01810036,0.004644923,0.001336887,0.001330861,0.001829867,0.02359264],"genre_scores_gemma":[0.3308193,0.007504615,0.6371496,0.01105846,0.003225594,0.006463397,0.000741703,0.001253129,0.001784222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5782111,"threshold_uncertainty_score":0.7130373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9690267653564798,"score_gpt":0.652948694286516,"score_spread":0.3160780710699638,"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."}}