When data are clustered due to longitudinal follow up or repeated sampling, special statistical methods need to be used to avoid bias and inefficiency. While in some clustered data the cluster size is pre-determined, in others it may be varying and correlated to the outcome of subunits, resulting in informative cluster size. When the cluster size is informative, standard statistical procedures that ignore cluster size may produce biased estimates. In this PI-initiated project, we will compare several methods that have been proposed in the literature to model data with informative cluster size, including within-cluster resampling, cluster weighted GEE, and joint modeling.
