This article is only available in the PDF format. Download the PDF to view the article, as well as its associated figures and tables.
We thank Dr Van Peenen for pointing out that industrial hazards can be studied with the case-control method. The "novelty" of our approach was not the selection of patients from a closed cohort, but the analysis of data according to the same principles of eligibility and prognostic susceptibility that would have been used in a well-designed randomized trial of therapy. Neglect of these principles can lead to bias in studying the effects of either industrial or therapeutic agents.
Horwitz RI, Feinstein AR. Alternative Strategies to Randomized Clinical Trials-Reply. JAMA. 1982;247(15):2100. doi:10.1001/jama.1982.03320400020024