GEE in Cancer Research
Cancer clinical trials often use a repeated measurement design in which individuals are randomly assigned to treatment arms and followed for measurements at intervals across a treatment period of fixed duration. In such studies, one of popular primary interests is the between-arm comparison of change rate in the expected value of a response variable over time. Because of the robustness to possible misspecification of the correlation structure among the repeated measurements, generalized estimating equation (GEE) method has been one of the most popular methods to fit the regression models and to test on the change rates. In this article, we review GEE method for analysis and sample size estimation methods for design of such trials. We consider the cases where the response variable is continuous or dichotomous.
