Despite the difficulties involved in designing drug epidemiology studies, t
hese studies are invaluable for investigating the unexpected adverse effect
s of drugs. The aim of this paper is to discuss various aspects of study de
sign, particularly those issues that are not easily found in either textboo
ks or review papers. We have also compared and contrasted drug epidemiology
with the randomized controlled trial (RCT) wherever possible. Drug epidemi
ology is especially useful in the many situations where the RCT is not suit
able, or even possible. The study base has to be defined before the appropr
iate cohort of subjects is assembled. If all of the cases are identified, t
hen a referent sample of controls may be assembled by random sampling of th
e study base. If all of the cases cannot be assembled, a hypothetical secon
dary base may need to be created. Preferably, only new-users of the drug sh
ould be included, and the risk-ratio will be different for acute users and
chronic users. Studies will usually only be possible when researching the u
nintended effects of drugs. It is difficult to study efficacy because of co
nfounding by indication. In occasional circumstances it may be possible to
study efficacy (examples are given). Discussion of the dangers of designing
with generalisability in mind is provided. Additionally, the similarities
in study design between drug epidemiology and the RCT are discussed in deta
il, as well as the design-characteristics that cannot be shared between the
two methods.