{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.212543,0.0002583414,0.001880022,0.0005822539,0.0003077633,0.002739454,0.002670497,0.00009352071,0.04624138],"category_scores_gemma":[0.6780707,0.0001004481,0.0007259574,0.0008982571,0.000190514,0.0005564521,0.0004852063,0.0002251008,0.03429928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001370304,"about_ca_system_score_gemma":0.0006002762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009502834,"about_ca_topic_score_gemma":0.0008742776,"domain_scores_codex":[0.9410298,0.02348204,0.005660715,0.001224218,0.02784283,0.0007603218],"domain_scores_gemma":[0.8930724,0.08638196,0.002750669,0.006066332,0.01117643,0.0005522375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006079454,0.0001846514,0.1652492,0.0001349672,0.000289415,0.00002078044,0.0005963743,0.000009575801,0.006672433,0.0189015,0.4825829,0.3252974],"study_design_scores_gemma":[0.001249947,0.0002530867,0.1296714,0.0004427691,0.0001404871,0.000006922198,0.0008606688,0.0008922131,0.004983091,0.2534061,0.6075106,0.0005827208],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1263184,0.001210512,0.8558578,0.006270718,0.0005483112,0.00277069,0.0003392695,0.00002462295,0.006659597],"genre_scores_gemma":[0.9777312,0.00006089478,0.01279089,0.00006680688,0.0002643964,0.0001266256,0.000005549437,0.00001980369,0.008933806],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8514128,"threshold_uncertainty_score":0.9982958,"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."}}