PRACTICING PHYSICIANS and statisticians may not seem to have many mutual interests, but perhaps they have more in common than is apparent at first. The purpose of this article is to describe a few statistical tools and to illustrate how these tools may be useful in the practice of medicine. As a starting point, consider a fairly frequently encountered medical problem, diabetes mellitus. According to some physicians, they believe that diabetics are best maintained at slightly elevated blood-glucose levels, but others feel that they should be maintained within limits of clinical normality. Which group is right or are they both right? And what is clinical normality and how is it determined? Suppose we consider the question of clinical normality first, partly because it is relatively easy to discuss and partly because it is a portion of the problem of maintaining diabetics in control. Normal Values According to one textbook,1