An incidence density sampling program for nested case-control analyses

Abstract

Background: The nested case-control design can be a very efficient approach to an epidemiological investigation. In order to obtain unbiased estimates of relative risk, controls should be selected by incidence density sampling, which involves matching each case to a sample of those who are at risk at the time of case occurrence.

Methods: This paper presents a simple computer program for incidence density sampling. This program was evaluated using data derived from a cohort study of mortality among workers employed in the nuclear weapons industry. Controls were selected for cases via incidence density sampling; an estimate of the exposure-mortality association was obtained via conditional logistic regression. After 100 iterations of this procedure, the average effect estimate was compared to the risk estimate obtained via proportional hazards regression. The same methods were used to evaluate a program for incidence density sampling that was proposed previously by Pearce in 1989.

Results: Relative risk estimates obtained from nested case-control analyses conducted using the incidence density sampling program reported in this paper are unbiased. In contrast, the program for incidence density sampling proposed by Pearce tended to produce biased relative risk estimates; the magnitude of bias increased with increasing numbers of controls selected per case.

Conclusions: The computer program described in this paper offers a simple approach to incidence density sampling for nested case-control analyses with exact matching on attained age and appropriate enumeration of the pool of eligible controls for each case. This method overcomes problems of bias inherent in a previously proposed program for incidence density sampling.