ABSTRACT
This chapter is the core of this monograph, providing an overview of several main areas in which joint models have been developed to address statistical issues that cannot be handled in separate analysis of longitudinal and survival data. Specifically, in the first three sections, we discuss joint models that are used as a tool to tackle the nonignorable missing data problem in longitudinal studies. The topics include monotone missing data caused by continuous or discrete event times, and longitudinal measurements with both monotone and intermittent missing values.
