The use of complex sampling designs in population-based case-control studie
s is becoming more common, particularly for sampling the control population
. This is prompted by all the usual cost and logistical benefits that are c
onferred by multistage sampling. Complex sampling has often been ignored in
analysis but, with the advent of packages like SUDAAN, survey-weighted ana
lyses that take account of the sample design can be carried out routinely.
This paper explores this approach and more efficient alternatives, which ca
n also be implemented by using readily available software.