Hypothesis testing in outcome-dependent sampling design under generalized linear models

In many large cohort studies, the major budge and cost typically arise from the assembling of primary covariates. Outcome-dependent sampling (ODS) designs are cost-effective sampling schemes which enrich the observed sample by selectively including certain subjects. We study the inference methods of hypothesis testing for a general ODS design under the generalized linear models. We develop a profile-likelihood-based family of tests and propose likelihood-ratio, Wald and score test statistics. Asymptotic properties of the proposed tests are established and the null limiting distributions are derived. The finite-sample behavior of the proposed methods is evaluated through simulation studies, and an application to a Wilms tumor data are illustrated.