In 1959 Wissinger and I published a report on the incidence of cutaneous eruptions due to sulfamethoxypyridazine.1 Simply, the method involved giving a standard dose of the drug to a large group of patients and counting the number of allergic reactions. Statisticians were consulted in regard to the design of the study. During the design phase, and especially while carrying out the study, it became evident that most of the uncertainty and probable error in the experiment were not problems of statistics. The difficulties were due to the vagueness and incompleteness of basic medical knowledge and to limitations in selection, supervision, and observation of patients in medical studies.
Simple counting methods involve fewer problems than do methods requiring measurement or judgment. This paper is concerned with the analysis of the simple counting study. An ideal mathematical model will be described and contrasted with the practical clinical study. I wish
ANDERSON PC. Problems in a Simple Two-Possibility Counting Study. Arch Dermatol. 1961;84(1):99–102. doi:10.1001/archderm.1961.01580130105016
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: