This article is only available in the PDF format. Download the PDF to view the article, as well as its associated figures and tables.
Some of Dr Gullen's points are well taken. They illustrate the complexity of the concepts that we were attempting to simplify and synthesize into a visual model, and they demonstrate the difficulty of doing so in a few words. The problem is the selection of words and their differing interpretations. Let us try again.
We referred to an advantage of the case-control study as making use of "already available (retrospective) data." Change that phrase to "collecting data on events (exposure factors) that have already occurred," and I believe that we and Dr Gullen would be in agreement. The essence of the retrospective approach is that it is one that selects and studies subjects who do or do not have the effect variable (ie, a disease or symptom) and that looks backward in biologic sequence to determine whether or not the cause variable (ie, an exposure) existed prior to
Gelfand HM, Doege TC. Epidemiologic Research-Reply. JAMA. 1978;239(25):2655. doi:10.1001/jama.1978.03280520027004
Customize your JAMA Network experience by selecting one or more topics from the list below.