Tasks in Statistical Inference for Studying Variation in Medicine

Abstract

When studying variation in medicine, traditional hypothesis-testing procedures are too limited to obtain useful inferences except in special situations. More generally, full probability modelling is necessary. Even a relatively simple example can illustrate this point rather dramatically. The development and application of full-probability methods for medical problems comprise exciting areas for statistical and medical researchers, especially if working together.(Med Care 1993; 31:YS103-YS110)