information on all health plan members in the pharmacy data base is
limited. For some studies36-38
we have carried out external adjustment using the method of Schneeweiss40.
We obtained information about the prevalence of possible confounding
variables such as cigarette smoking from samples of members who have
responded to a mailed questionnaire called the Member Health Survey. This
also permitted us to estimate the association between the confounder and use
of the drug being studied. We obtained the confounder/outcome association
from the literature.