The use and misuse of statistics in medical publications

Journal/Book: Reprinted from CLINICAL PHARMACOLOGY AND THERAPEUTICS St. Louis Vol. 1 No. 4 Pages 411-422 July-August 1960. 1960;

Abstract: Donald Mainland M.B. D.Sc.* New York N. Y. Department of Medical Statistics New York University School of Medicine This paper was written as part of a project entitled "Promotion of Biometrical Methods in Medical Research supported by a grant, RG-6100, from the National Institutes of Health, U.S. Public Health Service. *Address, 550 First Avenue, New York 18, N.Y. Commentary Research workers' widespread lack of understanding of the rationale of statistical techniques, and the frequent use of statistical tests as a substitute for thoughtful investigational design, meticulous work, and repetition of experiments, justify the antagonism to statistics exhibited by some experimenters. To one who has had personal experience of the way in which statistical thinking, as distinct from statistical arithmetic, can promote good investigation, this perversion of statistics is lamentable. It appears to be due, not so mach to investigators themselves, bat to the order in which experimenters' statistics was developed by the pioneers and presented to research workers, because Fisher's Statistical Methods" (1925) which discussed chiefly significance tests preceded by ten years his "Design of Experiments which showed how to plan experiments in order to obtain unambiguous inferences from the tests. Other causes of misunderstanding are discussed, and, in an effort to promote a more rational attitude to statistics, nine suggestions are presented. ___MH

Zurück | Weiter