IJE Advance Access originally published online on May 26, 2004
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
International Journal of Epidemiology, Volume 33, Number 3, pp. 612-613
IJE vol.33 no.3 © International Epidemiological Association 2004; all rights reserved.
Letter to the Editor |
What is a case-control study?
Department of Public Health and Epidemiology, The University of Birmingham, Edgbaston, Birmingham B15 2TT, UK. E-mail: t.marshall@bham.ac.uk
| The first 10% of the full text of this article appears below. |
What's in a name? That which we call a roseBy any other name would smell as sweet1
SirsCase-control studies are used in epidemiology to identify factors that differ in their frequency between case and control subjects, and which may therefore be interpreted as possible risk factors for the disease. The essence of the study design is that they look backwards, from disease to putative exposure.
The design has a long history, recently reviewed in two papers by Paneth, Susser and Susser.2,3 Probably the best-known study of this type is that of Doll and Hill,4 conducted in the late 1940s, which was one of the first rigorously designed studies to report on the lung cancersmoking association.
Recently, a number