Using covariate-specific disease prevalence information to increase the power of case-control studies

Abstract

Public registration databases and large cohort studies provide vital information on disease prevalence at various levels of a risk factor. This auxiliary information can be helpful in conducting statistical inference in a new study. We aim to develop a statistical procedure that improves the efficiency of the logistic regression model for a case-control study by utilizing auxiliary information on covariate-specific disease prevalence via a series of unbiased estimating equations. We adopt empirical likelihood for statistical inference, and demonstrate its advantages through simulation and an application.